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

    Neuronpedia

    INDEX
    Explanations

    phrases related to commitments and promises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uros
    -0.15
    izzo
    -0.15
    zas
    -0.15
    contro
    -0.15
     Verde
    -0.14
    ammen
    -0.14
    eyen
    -0.14
     beden
    -0.14
    uais
    -0.14
    ufen
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.19
    sdk
    0.16
    SDK
    0.16
    isposable
    0.14
     lemma
    0.14
    åŁ
    0.14
    erten
    0.14
    873
    0.14
    453
    0.14
     addCriterion
    0.14
    Act Density 0.004%

    No Known Activations