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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and adverbs indicating size or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enough
    -0.23
    son
    -0.21
    site
    -0.20
     Enough
    -0.19
    y
    -0.19
    sWith
    -0.19
    itude
    -0.18
    space
    -0.18
    sj
    -0.18
    side
    -0.18
    POSITIVE LOGITS
    -than
    0.79
     than
    0.63
    than
    0.60
    _than
    0.53
     THAN
    0.50
    Than
    0.49
     Than
    0.48
     niż
    0.38
    _THAN
    0.37
     než
    0.35
    Act Density 0.127%

    No Known Activations