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

    Neuronpedia

    INDEX
    Explanations

    specific phonetic or morphological patterns in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÌĢ
    -0.21
    Toy
    -0.16
    archy
    -0.16
    Ìģ
    -0.16
     Toy
    -0.16
    ória
    -0.15
     %+
    -0.15
    Ìģt
    -0.15
    odd
    -0.15
    _alias
    -0.15
    POSITIVE LOGITS
    ulo
    0.22
    coles
    0.21
    icas
    0.20
    culos
    0.20
    culo
    0.20
    ULO
    0.19
    nicas
    0.19
    lico
    0.19
    rico
    0.18
    frica
    0.17
    Act Density 0.026%

    No Known Activations