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

    Neuronpedia

    INDEX
    Explanations

    quantifiers indicating minimum amounts or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ONLY
    -0.16
     apenas
    -0.16
    licht
    -0.15
     actually
    -0.15
     exactly
    -0.15
     only
    -0.14
    isson
    -0.14
     hanya
    -0.14
    leston
    -0.14
    ONLY
    -0.14
    POSITIVE LOGITS
     partially
    0.28
     partly
    0.27
     partial
    0.22
    s
    0.20
     Partial
    0.18
     temporarily
    0.18
    once
    0.17
    .partial
    0.17
    partial
    0.17
     part
    0.16
    Act Density 0.038%

    No Known Activations