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

    Neuronpedia

    INDEX
    Explanations

    words indicating membership or inclusion within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gardner
    -0.20
     sinc
    -0.15
    elig
    -0.15
    erland
    -0.15
    ieder
    -0.15
    afia
    -0.14
    angstrom
    -0.14
    ADF
    -0.14
    istik
    -0.14
    inou
    -0.14
    POSITIVE LOGITS
    ÑĨеÑģ
    0.15
    ìī
    0.15
    alian
    0.14
    ense
    0.14
    207
    0.14
    ypes
    0.14
    не
    0.14
    enses
    0.13
    arel
    0.13
    achen
    0.13
    Act Density 0.001%

    No Known Activations