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

    Neuronpedia

    INDEX
    Explanations

    phrases related to contextual factors and specifications regarding a situation or application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asp
    -0.17
    aje
    -0.16
    itti
    -0.15
    zes
    -0.15
    asl
    -0.15
    esty
    -0.15
    esture
    -0.15
     twice
    -0.14
    efa
    -0.14
    isma
    -0.14
    POSITIVE LOGITS
    whether
    0.23
     whether
    0.21
     determines
    0.20
    æĺ¯åIJ¦
    0.20
     zda
    0.18
     determine
    0.18
     type
    0.17
    Whether
    0.17
    /how
    0.17
    TYPE
    0.17
    Act Density 0.191%

    No Known Activations