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

    Neuronpedia

    INDEX
    Explanations

    phrases signifying a location or a specific setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arkan
    -0.18
    egan
    -0.17
    rape
    -0.16
    edly
    -0.15
    zych
    -0.15
    olie
    -0.15
    wayne
    -0.15
    ars
    -0.14
    -columns
    -0.14
    adele
    -0.14
    POSITIVE LOGITS
     where
    0.20
    /time
    0.19
    ê³³
    0.19
    HOLDER
    0.18
    bos
    0.18
    /people
    0.17
    ettings
    0.17
    OfBirth
    0.17
    -temp
    0.16
    _compat
    0.16
    Act Density 0.036%

    No Known Activations