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

    Neuronpedia

    INDEX
    Explanations

    discussions and references about attention to detail

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

    insignificance or smallness

    np_acts-logits-general · gemini-2.0-flash

    small, minor, or insignificant things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ędziesz
    -0.60
    bootstrapcdn
    -0.58
    mergeFrom
    -0.58
    原始内容存档于
    -0.54
    migrationBuilder
    -0.52
     ModelExpression
    -0.49
     Infórmanos
    -0.48
     gespannt
    -0.46
     ***!
    -0.46
    anmar
    -0.44
    POSITIVE LOGITS
     small
    1.81
     minor
    1.73
    small
    1.67
     tiny
    1.61
    Small
    1.53
    minor
    1.53
     pequeños
    1.50
     little
    1.50
     smallest
    1.50
     SMALL
    1.50
    Act Density 0.382%

    No Known Activations