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

    Neuronpedia

    INDEX
    Explanations

    information related to authority and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aru
    -0.15
    isson
    -0.15
    halt
    -0.15
    fik
    -0.14
    aversable
    -0.14
    aida
    -0.14
    annies
    -0.14
    ubar
    -0.14
    aise
    -0.14
    MMdd
    -0.14
    POSITIVE LOGITS
    oco
    0.19
    825
    0.17
    даÑħ
    0.16
    enberg
    0.15
    anno
    0.14
    аÑĩе
    0.14
    YTE
    0.14
    iding
    0.14
    antha
    0.14
    dbus
    0.14
    Act Density 0.453%

    No Known Activations