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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Smy
    -0.17
     dev
    -0.15
     Roc
    -0.14
    soup
    -0.14
    sx
    -0.13
    _menus
    -0.13
    ário
    -0.13
    squ
    -0.13
    idders
    -0.13
    707
    -0.13
    POSITIVE LOGITS
    ´
    0.17
    ault
    0.15
    igest
    0.14
    erken
    0.14
    ERP
    0.14
    lej
    0.13
     Airlines
    0.13
     Ear
    0.13
    achen
    0.13
    ATEST
    0.13
    Act Density 1.876%

    No Known Activations