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

    Neuronpedia

    INDEX
    Explanations

    cryptic message-like patterns, likely related to encryption or code

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistical data within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enqu
    -0.75
     regener
    -0.74
     ability
    -0.73
     regenerate
    -0.72
    ©¶æ
    -0.71
     tram
    -0.69
     commissions
    -0.68
    aditional
    -0.66
     adolesc
    -0.65
     citiz
    -0.64
    POSITIVE LOGITS
    Asked
    1.36
    Related
    1.35
    Meanwhile
    1.35
    However
    1.30
    While
    1.29
    Advertisement
    1.29
    According
    1.29
    Among
    1.28
    But
    1.28
    Story
    1.26
    Act Density 0.610%

    No Known Activations