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

    Neuronpedia

    INDEX
    Explanations

    the word "never" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.74
    pB
    -0.74
    epiece
    -0.72
     Muffins
    -0.71
    StateToProps
    -0.71
    endsection
    -0.70
    raszam
    -0.70
    vidia
    -0.70
     IndexPath
    -0.70
    voegd
    -0.69
    POSITIVE LOGITS
     never
    2.07
     Never
    2.03
    Never
    1.96
     NEVER
    1.95
    NEVER
    1.94
    never
    1.93
     Nunca
    1.50
    Nunca
    1.44
     nunca
    1.39
     jamás
    1.37
    Act Density 0.039%

    No Known Activations