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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases involving expectations or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.86
     itſelf
    -0.78
    jména
    -0.75
    pośred
    -0.72
     Efq
    -0.69
     yoda
    -0.69
     Mahomet
    -0.67
     Pyrene
    -0.67
     Jefus
    -0.67
     sonne
    -0.66
    POSITIVE LOGITS
     the
    1.35
     a
    0.98
     its
    0.88
     be
    0.87
     their
    0.86
     our
    0.86
     TO
    0.83
     this
    0.79
     those
    0.78
     an
    0.77
    Act Density 0.566%

    No Known Activations