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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate uncertainty or vagueness in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.77
     autorytatywna
    -0.56
    IonicModule
    -0.56
     Савезне
    -0.56
     ddelweddau
    -0.54
     affaires
    -0.53
     tæ
    -0.53
    AutoScaleMode
    -0.52
     XNUMX
    -0.52
     SwitchCompat
    -0.52
    POSITIVE LOGITS
     somewhere
    1.31
    Somewhere
    1.30
    somewhere
    1.29
     Somewhere
    1.26
     someplace
    1.08
    Somebody
    1.02
    Someone
    0.95
     Somebody
    0.93
    Somehow
    0.93
     somehow
    0.92
    Act Density 0.149%

    No Known Activations