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

    Neuronpedia

    INDEX
    Explanations

    words that indicate uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edm
    -0.16
     ведÑĮ
    -0.15
    ŀ
    -0.15
    emean
    -0.14
    enco
    -0.14
    .ToTable
    -0.14
    endl
    -0.14
    .getenv
    -0.14
    alars
    -0.14
    anna
    -0.13
    POSITIVE LOGITS
    mente
    0.16
    ity
    0.15
    inson
    0.15
    -sex
    0.15
    -speaking
    0.14
    bia
    0.14
    unya
    0.14
    aro
    0.14
     Gaul
    0.14
     none
    0.13
    Act Density 0.038%

    No Known Activations