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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raz
    -0.16
     Mature
    -0.15
     spotlight
    -0.14
     Parm
    -0.14
    erson
    -0.14
     Majority
    -0.14
    iqu
    -0.14
     Russell
    -0.14
     cann
    -0.14
     Minority
    -0.14
    POSITIVE LOGITS
    _Tool
    0.17
     sexes
    0.15
     prote
    0.15
    atte
    0.14
    -toggler
    0.14
    วà¸Ķ
    0.14
    IFY
    0.14
    ombo
    0.14
    _RS
    0.14
    å·
    0.14
    Act Density 0.010%

    No Known Activations