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

    Neuronpedia

    INDEX
    Explanations

    references to names and pronunciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rary
    -0.16
    anonymous
    -0.15
    eph
    -0.15
    anni
    -0.14
    istar
    -0.14
    ordon
    -0.14
    ari
    -0.14
     rhet
    -0.13
    quip
    -0.13
    lien
    -0.13
    POSITIVE LOGITS
     spell
    0.65
     spelling
    0.58
    spell
    0.54
     Spell
    0.52
    Spell
    0.50
     spelled
    0.49
     SPELL
    0.47
    SPELL
    0.42
    _spell
    0.42
     spells
    0.42
    Act Density 0.265%

    No Known Activations