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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence delimiters

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

    Punctuation followed by common words

    np_acts-logits-general · gemini-2.0-flash

    words following a comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.95
     doubtnut
    -0.86
    styleType
    -0.85
     itſelf
    -0.83
     CreateTagHelper
    -0.83
     >=",
    -0.83
    esterday
    -0.81
     myſelf
    -0.79
     تانيه
    -0.79
    drawal
    -0.79
    POSITIVE LOGITS
     we
    0.97
     they
    0.84
    we
    0.77
     but
    0.75
     you
    0.72
     there
    0.71
     including
    0.69
     it
    0.69
     please
    0.68
    <eos>
    0.67
    Act Density 1.068%

    No Known Activations