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

    Neuronpedia

    INDEX
    Explanations

    phrases related to characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olars
    -0.16
    pire
    -0.16
    ünd
    -0.15
    asco
    -0.15
    sten
    -0.15
    hots
    -0.15
    åľ³
    -0.14
    окол
    -0.14
    eren
    -0.14
    allon
    -0.14
    POSITIVE LOGITS
    essler
    0.17
    _PROFILE
    0.16
    atorio
    0.15
    FT
    0.15
    IT
    0.14
    é²ľ
    0.14
    fee
    0.14
    udad
    0.14
    profile
    0.14
    .ft
    0.14
    Act Density 0.012%

    No Known Activations