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

    Neuronpedia

    INDEX
    Explanations

    uncommon symbols and characters

    oai_token-act-pair · gpt-3.5-turbo

    specific character sequences or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     restraints
    -0.66
     Fn
    -0.64
    esthetic
    -0.63
    urus
    -0.61
     Lei
    -0.60
    wcsstore
    -0.60
    Asian
    -0.60
     imaginable
    -0.59
    )).
    -0.59
     reneg
    -0.59
    POSITIVE LOGITS
    jong
    2.36
    æľ
    1.43
    iets
    0.86
    uden
    0.65
    arta
    0.64
     jud
    0.64
    jud
    0.62
    ictionary
    0.62
    ueller
    0.61
     ages
    0.60
    Act Density 0.002%

    No Known Activations