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

    Neuronpedia

    INDEX
    Explanations

    concepts related to certainty and ambiguity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iven
    -0.16
    IVEN
    -0.15
    zan
    -0.15
    ELLOW
    -0.13
    å¢
    -0.13
     only
    -0.13
    oux
    -0.13
    ÅĻez
    -0.13
    hora
    -0.13
    ICODE
    -0.13
    POSITIVE LOGITS
     ever
    0.27
     nÃło
    0.25
     EVER
    0.22
     except
    0.21
     nor
    0.20
    except
    0.20
     anymore
    0.19
     anywhere
    0.19
    ever
    0.18
     кÑĢоме
    0.17
    Act Density 0.089%

    No Known Activations