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

    Neuronpedia

    INDEX
    Explanations

    statements that convey meaning or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    him
    -0.17
    hoa
    -0.15
    how
    -0.15
     cómo
    -0.15
    aso
    -0.14
    ippo
    -0.14
    AtPath
    -0.14
    ัวà¸Ńย
    -0.14
    atern
    -0.14
    озв
    -0.14
    POSITIVE LOGITS
    lessly
    0.23
    fully
    0.23
    forth
    0.21
     there
    0.20
     we
    0.20
     fewer
    0.20
     they
    0.19
     no
    0.19
     you
    0.19
    0.18
    Act Density 0.034%

    No Known Activations