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

    Neuronpedia

    INDEX
    Explanations

    expressions related to imagining scenarios or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑĢа
    -0.17
    iddet
    -0.15
    comed
    -0.15
    ëĿ
    -0.14
    umbing
    -0.14
    annah
    -0.14
     Jones
    -0.14
    .foundation
    -0.14
    afort
    -0.14
    inan
    -0.13
    POSITIVE LOGITS
    ets
    0.17
    ede
    0.16
    aison
    0.16
     Duy
    0.15
    vil
    0.15
    eti
    0.15
    ilder
    0.14
    366
    0.14
    ì¦Ŀ
    0.14
    ous
    0.14
    Act Density 0.057%

    No Known Activations