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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "who"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allas
    -0.17
    INES
    -0.15
    MOV
    -0.14
    cased
    -0.14
    ÑĤÑı
    -0.14
    cents
    -0.14
     Tape
    -0.14
    proof
    -0.14
    uyo
    -0.14
     susp
    -0.14
    POSITIVE LOGITS
    asta
    0.16
    izi
    0.15
    ucher
    0.14
    CharacterSet
    0.14
    ocha
    0.14
    984
    0.14
     Bowman
    0.14
    çŀ
    0.14
    antly
    0.14
    oss
    0.13
    Act Density 0.083%

    No Known Activations