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

    Neuronpedia

    INDEX
    Explanations

    phrases that express intention or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gales
    -0.77
    ollection
    -0.74
     Seals
    -0.72
    flame
    -0.68
    entibus
    -0.68
     enfans
    -0.67
     vang
    -0.67
     zijne
    -0.66
     Jel
    -0.66
    Komentar
    -0.66
    POSITIVE LOGITS
     be
    0.95
    Gotta
    0.91
     gotta
    0.80
     Gotta
    0.79
    icoot
    0.76
     must
    0.74
     been
    0.74
    ArgsConstructor
    0.72
    Zeneca
    0.71
     take
    0.70
    Act Density 0.070%

    No Known Activations