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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or conditional situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onor
    -0.18
     tuy
    -0.17
    cke
    -0.15
    iddles
    -0.15
    orio
    -0.14
    oris
    -0.14
     totiž
    -0.14
    pora
    -0.14
    -layout
    -0.13
     Duy
    -0.13
    POSITIVE LOGITS
    ÎŃλ
    0.16
     latter
    0.16
    ais
    0.15
    NX
    0.14
     пÑĢиÑĤ
    0.14
    oose
    0.14
    ains
    0.14
    ZW
    0.14
     Greg
    0.14
     Bulk
    0.14
    Act Density 0.113%

    No Known Activations