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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    914
    -0.17
    .persistent
    -0.17
    pery
    -0.15
    asal
    -0.15
    cka
    -0.14
    enia
    -0.14
    ëĪĦ
    -0.14
    tha
    -0.14
    еÑĩно
    -0.14
    adem
    -0.13
    POSITIVE LOGITS
     ease
    0.42
    ease
    0.36
     abandon
    0.35
     Ease
    0.34
     precision
    0.31
    Ease
    0.29
     gusto
    0.29
     apl
    0.27
     efficiency
    0.26
     vigor
    0.25
    Act Density 0.167%

    No Known Activations