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

    Neuronpedia

    INDEX
    Explanations

    questions and assertions about doubt or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endphp
    -0.68
    GEBURTSDATUM
    -0.52
    دانشنامهٔ
    -0.52
     perciò
    -0.48
    MemoryWarning
    -0.47
    StoreMessageInfo
    -0.46
    __':
    -0.45
    __':
    -0.45
     Einfluß
    -0.44
    SequentialGroup
    -0.43
    POSITIVE LOGITS
     albeit
    0.70
     outright
    0.67
    albeit
    0.62
     seemingly
    0.60
    esque
    0.60
     purported
    0.59
     ostensibly
    0.59
     arguably
    0.58
    gatsby
    0.56
    nameof
    0.53
    Act Density 0.522%

    No Known Activations