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

    Neuronpedia

    INDEX
    Explanations

    references to capacity or fullness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oprot
    -0.60
    enumi
    -0.52
    SourceChecksum
    -0.51
     Negotiable
    -0.51
    Kanpo
    -0.49
    kret
    -0.48
    qrstuvwxyz
    -0.47
    umatic
    -0.47
    UNRELATED
    -0.47
    angal
    -0.46
    POSITIVE LOGITS
     filled
    1.62
     filling
    1.55
     fill
    1.48
     fills
    1.42
     Filled
    1.39
     full
    1.38
    Filling
    1.35
     Filling
    1.34
    full
    1.30
    filled
    1.28
    Act Density 0.278%

    No Known Activations