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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating compatibility or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eur
    -0.19
    SError
    -0.17
    hma
    -0.16
    eyen
    -0.16
    hed
    -0.16
    θεν
    -0.15
    hort
    -0.15
    edException
    -0.14
    undi
    -0.14
    ey
    -0.14
    POSITIVE LOGITS
    ting
    0.34
    TINGS
    0.26
    ment
    0.26
    gerald
    0.26
    tings
    0.26
     snug
    0.22
    TED
    0.22
     into
    0.21
    TING
    0.21
    ments
    0.21
    Act Density 0.022%

    No Known Activations