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

    Neuronpedia

    INDEX
    Explanations

    references to significant emotional or physical states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.52
    复制代码
    -0.45
     mourut
    -0.36
     itulah
    -0.32
     lyre
    -0.32
    ,’”
    -0.31
     Meski
    -0.31
     involucrados
    -0.30
     Kerajaan
    -0.30
    pernicus
    -0.30
    POSITIVE LOGITS
     somebody
    0.69
    httphttps
    0.63
     Somebody
    0.62
    rungsseite
    0.60
    Somebody
    0.57
    0.56
    somebody
    0.56
     autorytatywna
    0.55
     oneself
    0.54
     anybody
    0.54
    Act Density 0.654%

    No Known Activations