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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or thanks

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

    Precedes "!" or "." after greetings

    np_acts-logits-general · gemini-2.0-flash

    thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.76
    URLException
    -0.75
    uxxxx
    -0.73
    RTDA
    -0.70
     nonUne
    -0.70
    ConstraintMaker
    -0.70
     Italijanski
    -0.68
    PreInfinity
    -0.68
    ppuden
    -0.67
    mannian
    -0.67
    POSITIVE LOGITS
    ↵
    0.82
    ↵↵
    0.76
    <eos>
    0.66
    ↵↵↵
    0.65
    .
    0.58
    <bos>
    0.55
     -
    0.53
    ↵↵↵↵
    0.53
    !
    0.51
     anyway
    0.47
    Act Density 0.062%

    No Known Activations