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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and adverbs indicating quality or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anny
    -0.15
    raj
    -0.14
     Kahn
    -0.14
    .tf
    -0.14
    eczy
    -0.14
    ÐłÐĿ
    -0.14
     thumbnails
    -0.14
    леÑĩ
    -0.14
    YLE
    -0.13
    imson
    -0.13
    POSITIVE LOGITS
     than
    0.65
    -than
    0.56
    than
    0.54
    Than
    0.48
     THAN
    0.47
    _than
    0.47
     Than
    0.46
     niż
    0.40
     než
    0.36
    _THAN
    0.32
    Act Density 0.570%

    No Known Activations