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

    Neuronpedia

    INDEX
    Explanations

    uncertainty and speculation in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     presumably
    -0.73
    おそらく
    -0.71
     probably
    -0.71
    presumably
    -0.71
     probabilmente
    -0.69
     apparently
    -0.68
     evidently
    -0.66
     probablement
    -0.65
     probablemente
    -0.65
     provavelmente
    -0.64
    POSITIVE LOGITS
     someday
    0.71
     subconsciously
    0.61
     subconscious
    0.59
     sogar
    0.55
     unconsciously
    0.54
     TOO
    0.50
    RetentionPolicy
    0.50
     unintentionally
    0.49
     algún
    0.49
     unknowingly
    0.48
    Act Density 0.345%

    No Known Activations