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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their contributions in a research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.02
    AndEndTag
    -1.01
     myſelf
    -1.01
     pleaſure
    -0.97
     houſe
    -0.97
     purpoſe
    -0.97
     Anſ
    -0.95
     ſtre
    -0.94
     themſelves
    -0.93
    ſelf
    -0.92
    POSITIVE LOGITS
    JK
    0.49
     Jo
    0.45
     Mad
    0.43
     El
    0.42
    ph
    0.41
    jk
    0.41
     Siegel
    0.41
    .
    0.41
     L
    0.40
    il
    0.39
    Act Density 0.445%

    No Known Activations