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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions indicating relationships or conditions in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "to" followed by an article

    np_acts-logits-general · gemini-2.0-flash

    to followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.76
    jména
    -0.71
    pośred
    -0.70
     Mahomet
    -0.69
     itſelf
    -0.67
     eiffel
    -0.67
     yoda
    -0.65
     publick
    -0.64
     mohair
    -0.63
     sonne
    -0.63
    POSITIVE LOGITS
     the
    1.28
     a
    0.93
     TO
    0.88
     its
    0.84
    tems
    0.83
     zu
    0.80
     our
    0.79
    tolo
    0.77
     their
    0.77
    /$',
    0.77
    Act Density 0.537%

    No Known Activations