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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative forms of adjectives

    oai_token-act-pair · gpt-3.5-turbo

    words indicating size or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     �
    -0.82
     ãĢĮ
    -0.79
     Berks
    -0.72
     Pry
    -0.70
     Dres
    -0.69
     Frey
    -0.65
     Shepard
    -0.64
    onne
    -0.64
     Cheong
    -0.62
     Goff
    -0.61
    POSITIVE LOGITS
    "
    1.35
    ",
    1.27
    "!
    1.25
    %"
    1.21
    ";
    1.21
    "?
    1.17
    "—
    1.16
    usterity
    1.15
    "âĢ¦
    1.15
    ".
    1.14
    Act Density 0.214%

    No Known Activations