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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aña
    -0.15
    ardo
    -0.14
    iera
    -0.13
    CED
    -0.13
    agem
    -0.13
    erva
    -0.13
     Fro
    -0.13
    mey
    -0.13
    Ĺ
    -0.13
    lesi
    -0.13
    POSITIVE LOGITS
    000
    0.51
    500
    0.31
    Û°Û°Û°
    0.28
    ooo
    0.27
    ousand
    0.24
    600
    0.24
    OO
    0.23
    800
    0.23
    400
    0.22
    700
    0.21
    Act Density 0.089%

    No Known Activations