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

    Neuronpedia

    INDEX
    Explanations

    instances of whitespace or empty characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.79
     كومونز
    -0.68
     mũ
    -0.67
     Kota
    -0.63
    ).</
    -0.63
    homonymie
    -0.62
    ="'.$
    -0.61
    +/**
    -0.61
    DOCTYPE
    -0.59
    enscha
    -0.59
    POSITIVE LOGITS
     pipa
    0.71
     noastre
    0.69
    ↵↵
    0.68
    BeginContext
    0.67
     nostru
    0.65
    ↵↵↵↵
    0.65
    <blockquote>
    0.65
    OrNil
    0.64
     <<<<<<<<<<<<<<
    0.64
    ↵
    0.64
    Act Density 0.007%

    No Known Activations