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

    Neuronpedia

    INDEX
    Explanations

    comparisons and contrasts between items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exactly
    -0.60
     Phry
    -0.53
     anew
    -0.51
    Exactly
    -0.49
    Geografi
    -0.49
     exactly
    -0.49
     alſo
    -0.48
     Berber
    -0.48
    ungkinkan
    -0.48
     undetermined
    -0.47
    POSITIVE LOGITS
     previous
    1.08
     usual
    1.03
     HasFactory
    0.96
     typical
    0.94
    usual
    0.93
     kebanyakan
    0.93
     предыду
    0.92
    previous
    0.90
     competitors
    0.90
     traditional
    0.90
    Act Density 0.599%

    No Known Activations