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

    Neuronpedia

    INDEX
    Explanations

    intensifiers and modifiers that emphasize evaluations or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verted
    -0.18
    ially
    -0.16
    ulumi
    -0.16
    entiful
    -0.15
    iguous
    -0.14
    üyle
    -0.14
     proposal
    -0.14
    uzzle
    -0.14
    åĴ
    -0.14
    ughty
    -0.14
    POSITIVE LOGITS
     sooner
    0.20
     fewer
    0.20
     glad
    0.18
     often
    0.18
     few
    0.17
     true
    0.17
     impressed
    0.17
    few
    0.17
     tempted
    0.16
     Few
    0.16
    Act Density 0.157%

    No Known Activations