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

    Neuronpedia

    INDEX
    Explanations

    references to community and collective experiences, particularly surrounding psychological and emotional themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëį°ìĿ´íĬ¸
    -0.14
    ê³µ
    -0.14
    tü
    -0.13
    CallCheck
    -0.13
    ãĨ
    -0.12
    anford
    -0.12
    adoo
    -0.12
    stÅĻÃŃ
    -0.12
    ilestone
    -0.12
    _parms
    -0.12
    POSITIVE LOGITS
     know
    1.10
     knows
    1.04
     Know
    0.94
    know
    0.92
     knew
    0.90
    çŁ¥éģĵ
    0.87
     KNOW
    0.86
     knowing
    0.86
    Know
    0.82
    -know
    0.75
    Act Density 0.778%

    No Known Activations