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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "We," indicating a focus on collective actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shed
    -0.15
    สà¸Ķ
    -0.15
    fty
    -0.15
    lass
    -0.15
     над
    -0.15
    rench
    -0.14
     shed
    -0.14
    lasses
    -0.14
    æļ´
    -0.14
    >Returns
    -0.14
    POSITIVE LOGITS
    raquo
    0.17
    ueblo
    0.16
     Hall
    0.15
     ((__
    0.15
    agi
    0.15
    iÄį
    0.15
    orget
    0.14
    Hall
    0.14
    ruk
    0.14
    ülük
    0.14
    Act Density 0.007%

    No Known Activations