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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to classification and reclining

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zelf
    -0.16
    665
    -0.16
    -fold
    -0.14
    icus
    -0.14
    edor
    -0.14
    ED
    -0.14
    steen
    -0.14
    нÑĸв
    -0.14
    çī©
    -0.14
    fold
    -0.14
    POSITIVE LOGITS
    erator
    0.22
    ustering
    0.21
    ipse
    0.21
    airs
    0.20
    USTER
    0.20
    ipt
    0.19
    arend
    0.18
    er
    0.18
    ench
    0.17
    usive
    0.17
    Act Density 0.018%

    No Known Activations