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

    Neuronpedia

    INDEX
    Explanations

    words related to behavioral effects or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to behavioral studies and psychology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bleacher
    -0.81
    shall
    -0.80
    vy
    -0.79
    nz
    -0.78
    ym
    -0.78
    eous
    -0.77
    eur
    -0.73
    biz
    -0.73
    ources
    -0.73
    zzo
    -0.71
    POSITIVE LOGITS
     behavioral
    1.21
    avior
    1.12
     behavi
    1.09
     behavioural
    1.03
     behaviors
    1.00
     behavior
    0.98
     Behavioral
    0.94
    behavior
    0.92
     Behavior
    0.88
    Beh
    0.87
    Act Density 0.009%

    No Known Activations