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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of a strong subject or character involved in actions or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strap
    -0.17
    .sap
    -0.16
    @update
    -0.15
    argas
    -0.14
    ifer
    -0.14
    amarin
    -0.14
    ilha
    -0.14
    @show
    -0.14
     fark
    -0.13
     Academ
    -0.13
    POSITIVE LOGITS
    anner
    0.15
    iglia
    0.14
     Hann
    0.14
    ↵
    0.14
    esis
    0.14
     cr
    0.13
    ergy
    0.13
     Bord
    0.13
    _defaults
    0.13
    ANTI
    0.13
    Act Density 0.107%

    No Known Activations