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

    Neuronpedia

    INDEX
    Explanations

    words related to compounds or composite aspects

    oai_token-act-pair · gpt-3.5-turbo

    the word "comp" and its various forms, indicating a focus on concepts related to compounding or cumulative effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whites
    -0.67
     Millennium
    -0.66
    ggle
    -0.64
     Roses
    -0.64
     Spectrum
    -0.60
     Reich
    -0.60
     friendships
    -0.59
     Bul
    -0.58
    FORE
    -0.58
     Rabbit
    -0.57
    POSITIVE LOGITS
    artments
    1.51
    endium
    1.49
    ulsive
    1.39
    ounding
    1.26
    unction
    1.25
    actor
    1.25
    ilers
    1.24
    ressive
    1.22
    ortment
    1.22
    ressing
    1.19
    Act Density 0.012%

    No Known Activations