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

    Neuronpedia

    INDEX
    Explanations

    references to formal documents or authoritative sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfavorable
    -0.15
    —"
    -0.15
     Whilst
    -0.15
    áze
    -0.14
     Behavior
    -0.14
     âĢŀ
    -0.14
    Ngh
    -0.14
    ît
    -0.14
    .fore
    -0.14
     behavior
    -0.14
    POSITIVE LOGITS
     Dublin
    0.18
    .ie
    0.17
     Irish
    0.16
     Corm
    0.16
    eneg
    0.15
     ‘
    0.15
     Cork
    0.15
     Ireland
    0.15
    enu
    0.14
    Dub
    0.14
    Act Density 0.000%

    No Known Activations