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

    Neuronpedia

    INDEX
    Explanations

    phrases related to analyzing details or providing in-depth information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.79
    AIN
    -0.76
    Sov
    -0.72
     Mania
    -0.68
     Thieves
    -0.68
     Freak
    -0.64
    onso
    -0.64
     Pengu
    -0.63
    heim
    -0.63
    ains
    -0.63
    POSITIVE LOGITS
     proximity
    1.08
     minded
    0.93
     resemblance
    0.91
     shave
    0.86
    paren
    0.85
     relatives
    0.84
     enough
    0.81
     ties
    0.81
     confid
    0.81
     relations
    0.79
    Act Density 0.041%

    No Known Activations