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

    Neuronpedia

    INDEX
    Explanations

    action-oriented words and phrases related to decision-making and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     parc
    -0.15
    Ŀ
    -0.15
    ulas
    -0.15
     Lans
    -0.14
    омен
    -0.14
    antis
    -0.14
    SDK
    -0.14
     Hol
    -0.14
    ìħ
    -0.14
    ìĥ
    -0.14
    POSITIVE LOGITS
    orz
    0.17
    uele
    0.15
    nal
    0.15
    orget
    0.15
    mage
    0.15
    enso
    0.14
    nage
    0.14
    ledger
    0.14
    continue
    0.14
    illez
    0.13
    Act Density 0.009%

    No Known Activations