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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical and psychological conditions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    eous
    -0.73
    smanship
    -0.64
    urat
    -0.61
    liness
    -0.60
    enthal
    -0.59
    yy
    -0.58
    pez
    -0.58
    eem
    -0.57
    worthy
    -0.56
    shall
    -0.56
    POSITIVE LOGITS
    avior
    0.78
     behavioral
    0.72
     conditioning
    0.68
     ecology
    0.64
     biologists
    0.61
     genetics
    0.60
     traits
    0.59
    CHAT
    0.58
     regression
    0.58
     behavioural
    0.58
    Act Density 4.217%

    No Known Activations