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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "never" indicating negation or past denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Muffins
    -0.80
    stdc
    -0.76
    KommentareTeilen
    -0.74
    :]:
    -0.74
     للمعارف
    -0.72
    DispatchToProps
    -0.72
    raszam
    -0.72
    voegd
    -0.70
    cioso
    -0.69
    vidia
    -0.69
    POSITIVE LOGITS
     Never
    1.53
     never
    1.49
     NEVER
    1.48
    NEVER
    1.47
    Never
    1.46
    never
    1.42
     EVER
    1.16
     Nunca
    1.16
    Nunca
    1.10
     Ever
    1.09
    Act Density 0.047%

    No Known Activations