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

    Neuronpedia

    INDEX
    Explanations

    expressions of positivity and admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oko
    -0.18
    oric
    -0.18
    -0.17
    orie
    -0.16
    edb
    -0.15
    elem
    -0.15
     ok
    -0.14
    ed
    -0.14
     greatness
    -0.14
    .lv
    -0.14
    POSITIVE LOGITS
    -grand
    0.21
    lest
    0.21
    -looking
    0.20
    ideos
    0.16
    ulously
    0.16
    mente
    0.15
     Reputation
    0.15
    acon
    0.15
    oplast
    0.15
    ikip
    0.15
    Act Density 0.053%

    No Known Activations