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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causes or reasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.16
    inkel
    -0.15
    ynchronize
    -0.15
    {:
    -0.14
    .Generated
    -0.14
    resse
    -0.14
    annis
    -0.14
    finity
    -0.14
    isters
    -0.14
    elder
    -0.14
    POSITIVE LOGITS
    er
    0.17
    rone
    0.15
     none
    0.14
    geries
    0.14
    aging
    0.14
    ĭ
    0.14
     Dispatch
    0.14
    razier
    0.14
     desp
    0.14
    stro
    0.14
    Act Density 0.028%

    No Known Activations