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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capabilities or abilities related to various tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ers
    -0.17
    asaki
    -0.17
    rze
    -0.15
    apus
    -0.15
    iá»ĩn
    -0.15
    mers
    -0.14
    erk
    -0.14
    ulen
    -0.14
    ilion
    -0.14
    allen
    -0.14
    POSITIVE LOGITS
    -bodied
    0.20
    rium
    0.16
    olo
    0.14
     Craigslist
    0.14
    eview
    0.14
    idades
    0.14
    rary
    0.13
    /disable
    0.13
    ehir
    0.13
    ointments
    0.13
    Act Density 0.044%

    No Known Activations