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

    Neuronpedia

    INDEX
    Explanations

    text that refers to mechanisms or processes in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stones
    -0.82
    Попис
    -0.81
    RetentionPolicy
    -0.80
     ProtoMessage
    -0.76
     Sev
    -0.74
    Gord
    -0.72
    /***/
    -0.72
     héro
    -0.71
     Astoria
    -0.71
    phalt
    -0.71
    POSITIVE LOGITS
     mechanisms
    1.44
    Mechanisms
    1.44
     MECHAN
    1.42
     Mechanisms
    1.40
     mechanism
    1.36
     Mechanism
    1.33
    mechanism
    1.26
    mechan
    1.24
    Mechanism
    1.15
    MECHAN
    1.13
    Act Density 0.096%

    No Known Activations