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

    Neuronpedia

    INDEX
    Explanations

    characters with accents and special characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols and punctuation marks indicating emphasis or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oris
    -0.71
     largeDownload
    -0.68
    abase
    -0.67
    iewicz
    -0.66
    anol
    -0.66
    ovie
    -0.64
     CLSID
    -0.64
    unciation
    -0.63
     Charleston
    -0.63
     Murdoch
    -0.61
    POSITIVE LOGITS
    dating
    1.02
    ¡
    0.97
    bably
    0.89
    STEM
    0.83
    ت
    0.82
    ban
    0.82
    ×ķ
    0.81
    ading
    0.80
    âĶĢâĶĢâĶĢâĶĢ
    0.80
    Ùħ
    0.80
    Act Density 0.003%

    No Known Activations