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

    Neuronpedia

    INDEX
    Explanations

    dialogue introductions and punctuation marks that indicate speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÂŁ
    -0.19
    vsp
    -0.16
     Inn
    -0.16
    allen
    -0.15
    igger
    -0.14
     chiff
    -0.14
    .fm
    -0.14
    oot
    -0.14
     Trav
    -0.13
    áu
    -0.13
    POSITIVE LOGITS
    ervo
    0.15
    erville
    0.15
    ayers
    0.15
    rchive
    0.14
    ô
    0.14
    065
    0.14
    ARGIN
    0.14
    ustin
    0.14
     AndAlso
    0.14
     rodin
    0.13
    Act Density 0.003%

    No Known Activations