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

    Neuronpedia

    INDEX
    Explanations

    sets of numerical data related to weight comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.03
     ſever
    -0.86
     themſelves
    -0.86
    TintMode
    -0.85
     Anfitrión
    -0.84
     raiſ
    -0.83
     purpoſe
    -0.83
     ſche
    -0.82
     iſt
    -0.80
     Diſ
    -0.80
    POSITIVE LOGITS
     
    0.57
    </h2>
    0.55
     I
    0.53
    </em>
    0.50
     lui
    0.48
     he
    0.48
     Ar
    0.48
    ://
    0.46
     C
    0.46
    ↵↵
    0.46
    Act Density 0.815%

    No Known Activations