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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and interactions with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.59
     
    -0.58
    сет
    -0.54
    ieta
    -0.53
    </h2>
    -0.51
     “
    -0.51
    ssch
    -0.48
     Li
    -0.47
     A
    -0.46
     for
    -0.46
    POSITIVE LOGITS
     myſelf
    1.00
     HasFactory
    0.81
     reaſon
    0.79
     anſ
    0.79
     Monfieur
    0.76
    TestBed
    0.76
    rungsseite
    0.76
     himſelf
    0.74
     chofe
    0.74
     muſt
    0.74
    Act Density 0.318%

    No Known Activations