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

    Neuronpedia

    INDEX
    Explanations

    instances of the beginning or starting point of a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crowley
    -0.79
    providedIn
    -0.72
    ValueStyle
    -0.71
     Egal
    -0.71
     erw
    -0.70
     HttpHeaders
    -0.69
     Flan
    -0.68
     Ede
    -0.68
    ülé
    -0.68
    DockStyle
    -0.67
    POSITIVE LOGITS
     MUCH
    1.15
    Mucho
    0.97
    much
    0.92
     much
    0.92
    Much
    0.92
     Much
    0.91
    mucho
    0.88
     Uch
    0.87
     dużo
    0.78
     Kuch
    0.77
    Act Density 0.068%

    No Known Activations