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

    Neuronpedia

    INDEX
    Explanations

    terms indicating doubt or minimal presence

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    شف
    -0.66
     Stevenson
    -0.65
     bè
    -0.65
     Anastasia
    -0.65
     maestra
    -0.64
    circledR
    -0.63
     Folsom
    -0.63
    downarrow
    -0.62
    Bent
    -0.60
     récompenses
    -0.60
    POSITIVE LOGITS
     Hardly
    1.11
     barely
    1.02
     hardly
    1.00
     scarcely
    0.91
     insuffisamment
    0.81
    ftances
    0.80
    %";
    0.75
     HasFactory
    0.74
    ينما
    0.74
     Theſe
    0.73
    Act Density 0.003%

    No Known Activations