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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate detailed discussion and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atk
    -0.17
     Schmidt
    -0.16
    adlo
    -0.15
    el
    -0.14
     Feld
    -0.14
    ambi
    -0.14
    à¸ĩาà¸Ļ
    -0.14
    ua
    -0.14
    rary
    -0.14
     Hud
    -0.13
    POSITIVE LOGITS
     detail
    0.47
    detail
    0.39
     Detail
    0.35
    -detail
    0.33
    Detail
    0.32
    _detail
    0.30
    .detail
    0.30
     detal
    0.29
     detalle
    0.29
     depth
    0.24
    Act Density 0.130%

    No Known Activations