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

    Neuronpedia

    INDEX
    Explanations

    repeated conjunctions that suggest alternatives or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rish
    -0.16
    oS
    -0.15
    "urls
    -0.14
    amon
    -0.14
    бо
    -0.14
    .="
    -0.14
    าà¸
    -0.14
    _vert
    -0.14
    angstrom
    -0.13
    imity
    -0.13
    POSITIVE LOGITS
    ients
    0.22
    acles
    0.20
    /
    0.18
    yx
    0.17
    de
    0.17
    lando
    0.17
    fer
    0.16
    wel
    0.16
    ign
    0.16
    thon
    0.16
    Act Density 0.134%

    No Known Activations