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

    Neuronpedia

    INDEX
    Explanations

    contrasting viewpoints or dichotomies in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loi
    -0.18
    uzzi
    -0.17
    æıIJ
    -0.16
    ree
    -0.15
    518
    -0.15
    REE
    -0.14
     Garn
    -0.14
    andan
    -0.14
    707
    -0.14
    orida
    -0.14
    POSITIVE LOGITS
     either
    0.27
     Either
    0.26
    Either
    0.22
     EITHER
    0.21
     binary
    0.20
    binary
    0.20
    either
    0.20
     Binary
    0.19
    -binary
    0.18
    anga
    0.16
    Act Density 0.111%

    No Known Activations