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

    Neuronpedia

    INDEX
    Explanations

    terms associated with habitual actions or expectations

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

    like "also", "still", and "then"

    np_acts-logits-general · gemini-2.0-flash

    also / then / still / only followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jefus
    -0.87
     Theſe
    -0.87
     Chriftian
    -0.79
     Efq
    -0.79
     becauſe
    -0.76
     pleaſure
    -0.69
     ftate
    -0.68
     Diſ
    -0.67
     purpoſe
    -0.67
     Eſ
    -0.66
    POSITIVE LOGITS
     also
    1.07
     not
    1.03
     likely
    1.01
     going
    0.95
     always
    0.95
     still
    0.92
     actually
    0.88
     able
    0.87
     just
    0.85
     considered
    0.84
    Act Density 0.289%

    No Known Activations