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

    Neuronpedia

    INDEX
    Explanations

    the word "who" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogen
    -0.16
    vas
    -0.15
    .useState
    -0.14
    Č↵
    -0.14
    çĻ
    -0.13
    ugin
    -0.13
    isme
    -0.13
    ting
    -0.13
    bindung
    -0.13
    vd
    -0.13
    POSITIVE LOGITS
    eto
    0.16
    esto
    0.16
    lesia
    0.15
    esti
    0.14
    .Sin
    0.14
    OCKET
    0.14
     Jensen
    0.14
     sf
    0.14
    .rpm
    0.14
    raise
    0.14
    Act Density 0.114%

    No Known Activations