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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ø·ÙĦ
    -0.15
    vido
    -0.15
     Nest
    -0.15
    amon
    -0.15
    ajas
    -0.15
     Naj
    -0.15
    arsity
    -0.14
    Cream
    -0.14
    accine
    -0.14
    ezier
    -0.14
    POSITIVE LOGITS
    èĪ
    0.19
     eskort
    0.17
     prelim
    0.15
     ASS
    0.14
    -know
    0.14
     ÑģледÑĥÑİÑī
    0.14
    EDA
    0.14
    éģ
    0.13
     considering
    0.13
     Want
    0.13
    Act Density 0.068%

    No Known Activations