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

    Neuronpedia

    INDEX
    Explanations

    adverbs or adjectives emphasizing the literal nature of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.69
    SBATCH
    -0.66
    ouncil
    -0.60
     quæ
    -0.58
    }{*}{
    -0.57
    cq
    -0.57
     Autorisations
    -0.56
     beginnetje
    -0.55
     Marqu
    -0.55
     Mayfield
    -0.54
    POSITIVE LOGITS
     literally
    1.52
     Literally
    1.45
    Literally
    1.44
     literal
    1.43
    literally
    1.40
    literal
    1.26
     literalmente
    1.20
     litté
    1.15
     Literal
    1.13
    LITERAL
    1.00
    Act Density 0.046%

    No Known Activations