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

    Neuronpedia

    INDEX
    Explanations

    punctuation and expressive statements in dialogue

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

    Dialogue or quoted speech

    np_acts-logits-general · gemini-2.0-flash

    end of speech followed by new sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forti
    -0.61
     Majefty
    -0.59
     Efq
    -0.57
     houſe
    -0.56
     Conſ
    -0.53
    κει
    -0.52
    asmuch
    -0.52
     Houſe
    -0.52
     owed
    -0.51
     wherefore
    -0.50
    POSITIVE LOGITS
     he
    0.80
     she
    0.76
     we
    0.74
     you
    0.72
     they
    0.71
     someone
    0.70
     came
    0.68
     whispered
    0.67
     comes
    0.65
     I
    0.63
    Act Density 0.032%

    No Known Activations