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

    Neuronpedia

    INDEX
    Explanations

    HTML coding symbols

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific symbols or characters, particularly the character "Ŀ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chnology
    -0.85
    anmar
    -0.81
     satell
    -0.79
     encount
    -0.77
    imore
    -0.76
    inav
    -0.76
     untouched
    -0.76
     overloaded
    -0.76
     coerc
    -0.75
    ciplinary
    -0.75
    POSITIVE LOGITS
    ï¸ı
    1.15
     Asked
    1.05
     Ibid
    1.03
    <|endoftext|>
    1.02
     Obviously
    0.99
     Unfortunately
    0.99
     However
    0.98
     Additionally
    0.98
    ONSORED
    0.97
     Therefore
    0.96
    Act Density 0.134%

    No Known Activations