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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    112
    -0.16
     forState
    -0.16
    enson
    -0.15
     Sor
    -0.15
    ousse
    -0.14
    anik
    -0.14
     may
    -0.14
     Lance
    -0.14
    vale
    -0.14
    348
    -0.14
    POSITIVE LOGITS
     being
    0.24
     être
    0.20
    being
    0.20
    Being
    0.20
     být
    0.20
     Being
    0.19
     having
    0.19
     essere
    0.19
     бÑĭÑĤÑĮ
    0.19
     faire
    0.19
    Act Density 0.067%

    No Known Activations