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

    Neuronpedia

    INDEX
    Explanations

    Latin words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    the use of particular characters or symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Territory
    -0.70
     accelerated
    -0.70
     Publications
    -0.68
     Expend
    -0.66
     targeted
    -0.66
     Horizons
    -0.66
     lod
    -0.65
     Mirage
    -0.64
     geographically
    -0.64
     Philippe
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.32
    $
    0.98
    ternity
    0.95
    sorry
    0.92
    cffffcc
    0.90
    reci
    0.90
    @#
    0.90
    shit
    0.89
    ¯
    0.89
    hello
    0.88
    Act Density 0.160%

    No Known Activations