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

    Neuronpedia

    INDEX
    Explanations

    words related to proximity or accompaniment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ek
    -0.15
    ummer
    -0.14
    odal
    -0.13
    oris
    -0.13
    anh
    -0.13
    eros
    -0.13
    agon
    -0.13
    _ASSUME
    -0.13
    utations
    -0.13
    جز
    -0.12
    POSITIVE LOGITS
    fra
    0.18
    ward
    0.16
    LastError
    0.16
    wards
    0.15
    neath
    0.15
     the
    0.14
    \/\/
    0.14
    füh
    0.14
    estar
    0.14
    ought
    0.14
    Act Density 0.146%

    No Known Activations