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

    Neuronpedia

    INDEX
    Explanations

    words associated with discussions or mentions of ability or possibility

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions indicating inability or impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RAD
    -0.82
     airs
    -0.76
     Gleaming
    -0.67
     Sandwich
    -0.65
     mixed
    -0.65
    anwhile
    -0.65
     theaters
    -0.63
    çīĪ
    -0.62
     Trojan
    -0.61
     Hir
    -0.60
    POSITIVE LOGITS
    Ķ
    1.40
    «
    1.32
    ĵ
    1.30
    ij
    1.28
    ¼
    1.28
    ¢
    1.27
    £
    1.26
    ı
    1.23
    ķ
    1.23
    ¨
    1.22
    Act Density 0.071%

    No Known Activations