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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "never."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vidia
    -0.81
    AOC
    -0.76
     Lübeck
    -0.73
    deaux
    -0.73
    ்ச
    -0.72
     Muffins
    -0.72
     PIB
    -0.71
    oforte
    -0.71
     Otis
    -0.71
    شة
    -0.70
    POSITIVE LOGITS
     never
    2.39
     Never
    2.21
     NEVER
    2.18
    never
    2.17
    Never
    2.13
    NEVER
    2.06
     Nunca
    1.61
    Nunca
    1.60
     nunca
    1.55
    nunca
    1.36
    Act Density 0.031%

    No Known Activations