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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.74
    ikkert
    -0.72
    SequentialGroup
    -0.72
    BASELINE
    -0.71
    setVerticalGroup
    -0.69
     الدولى
    -0.67
    parsedMessage
    -0.65
     présidenti
    -0.61
    Portály
    -0.59
    themselves
    -0.59
    POSITIVE LOGITS
     surla
    0.48
    itability
    0.47
    ppen
    0.47
     Lun
    0.45
    tope
    0.42
     undergoes
    0.42
     actionMode
    0.42
    Referencie
    0.42
    ind
    0.42
    de
    0.41
    Act Density 0.241%

    No Known Activations