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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to comparisons and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ated
    -0.17
    ury
    -0.15
    /software
    -0.15
    upil
    -0.15
    icia
    -0.14
    ery
    -0.14
    èį·
    -0.14
    /read
    -0.14
    vic
    -0.14
    uries
    -0.14
    POSITIVE LOGITS
    rios
    0.16
    chg
    0.15
    .locals
    0.15
    iesen
    0.15
     minded
    0.15
    encing
    0.14
     unfavor
    0.14
    oleon
    0.14
    tures
    0.14
    ollar
    0.14
    Act Density 0.048%

    No Known Activations