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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs denoting the ability or potential for action

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and adverbs that indicate capability or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wan
    -0.64
     Bed
    -0.63
    Secure
    -0.61
    price
    -0.60
    Rah
    -0.60
     Chains
    -0.58
     Gong
    -0.58
    stead
    -0.58
    ï¸ı
    -0.58
    Party
    -0.57
    POSITIVE LOGITS
     behav
    0.95
    rious
    0.88
    matical
    0.75
    matically
    0.74
     endeavour
    0.74
     destro
    0.73
     endeavor
    0.70
    rium
    0.69
     talents
    0.69
     abilities
    0.68
    Act Density 0.174%

    No Known Activations