Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to obstacles and challenges in communication or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Susceptible, open, or vulnerable states/conditions

    np_acts-logits-general · gemini-2.0-flash

    open to or vulnerable to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.79
    GEBURTSDATUM
    -0.71
     ProtoMessage
    -0.68
    <bos>
    -0.65
    SequentialGroup
    -0.58
    ThroughAttribute
    -0.56
    HideFlags
    -0.56
     doInBackground
    -0.55
    Recovered
    -0.55
    MessageState
    -0.54
    POSITIVE LOGITS
     susceptible
    1.43
     vulnerable
    1.42
     vulnerability
    1.38
     prone
    1.37
     susceptibility
    1.35
     suscep
    1.15
     Vulnerable
    1.13
     vulnerables
    1.11
     vulner
    1.08
     Vulnerability
    1.08
    Act Density 0.509%

    No Known Activations