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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.16
    fighters
    -0.16
    eq
    -0.15
    太éĥİ
    -0.15
    enko
    -0.15
    kre
    -0.15
    irut
    -0.15
    gli
    -0.15
    urons
    -0.15
    ey
    -0.15
    POSITIVE LOGITS
    iginal
    0.27
    ourke
    0.23
    hea
    0.23
    ignal
    0.23
    leans
    0.22
    tega
    0.21
    .scalablytyped
    0.21
    naments
    0.20
    chestra
    0.19
    isha
    0.17
    Act Density 0.042%

    No Known Activations