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

    Neuronpedia

    INDEX
    Explanations

    phrases that express categorization or qualification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.45
     HasFactory
    -0.40
    Manbalar
    -0.40
     pinulongan
    -0.39
    AnchorStyles
    -0.39
     thermique
    -0.37
    Билгалдахарш
    -0.36
    +#+#
    -0.36
     kasarigan
    -0.35
    তথ্যসূত্র
    -0.34
    POSITIVE LOGITS
     Kinda
    0.77
     sorta
    0.73
    Kinda
    0.73
     kinda
    0.65
     Somewhat
    0.64
    Somewhat
    0.64
    kinda
    0.63
    なんとなく
    0.61
     somewhat
    0.61
     quasi
    0.59
    Act Density 0.188%

    No Known Activations