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

    Neuronpedia

    INDEX
    Explanations

    the word "which" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aylight
    -0.15
    uese
    -0.14
    asion
    -0.14
    ings
    -0.14
    ières
    -0.14
    اÙĨÙĩ
    -0.14
    æk
    -0.13
    iet
    -0.13
    onent
    -0.13
    ista
    -0.13
    POSITIVE LOGITS
    soever
    0.22
    irl
    0.16
    /how
    0.15
    ãģ¾ãģ¾
    0.15
    pher
    0.15
     Ñģаме
    0.15
    ynchron
    0.14
    -way
    0.13
    -sex
    0.13
    -ever
    0.13
    Act Density 0.026%

    No Known Activations