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

    Neuronpedia

    INDEX
    Explanations

    questions that begin with "how do."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ient
    -0.18
    è¡
    -0.16
    enor
    -0.15
    mey
    -0.15
    ayi
    -0.15
    lings
    -0.15
    اÙĬÙĦ
    -0.15
    ɵ
    -0.15
    UU
    -0.15
    anto
    -0.15
    POSITIVE LOGITS
     you
    0.19
     they
    0.18
     we
    0.17
    /w
    0.17
    actic
    0.17
    /c
    0.16
     th
    0.16
    ñana
    0.16
    oming
    0.15
    't
    0.15
    Act Density 0.034%

    No Known Activations