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

    Neuronpedia

    INDEX
    Explanations

    references to percentages in various contexts

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

    per cent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ooo
    -0.49
    apie
    -0.45
    avan
    -0.45
    iano
    -0.44
    ows
    -0.44
    ep
    -0.43
    FP
    -0.41
    aki
    -0.41
    agar
    -0.40
    eager
    -0.40
    POSITIVE LOGITS
     CURIAM
    0.74
     nahilalakip
    0.62
     quæ
    0.60
     characterised
    0.58
    enterOuterAlt
    0.56
     colour
    0.56
    帖最后由
    0.56
    InputBorder
    0.55
     Normdatei
    0.55
     cent
    0.55
    Act Density 0.011%

    No Known Activations