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

    Neuronpedia

    INDEX
    Explanations

    references to academic programs and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argas
    -0.16
    zcze
    -0.16
    orthand
    -0.16
    ocos
    -0.15
    illis
    -0.15
     Soda
    -0.15
    .mods
    -0.15
    nos
    -0.15
    bose
    -0.14
    OURSE
    -0.14
    POSITIVE LOGITS
     Newman
    0.17
    apo
    0.17
    PHA
    0.15
    thers
    0.15
    ateur
    0.14
    |#
    0.14
    opoulos
    0.14
     Vide
    0.14
    ırak
    0.14
    ouched
    0.14
    Act Density 0.350%

    No Known Activations