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

    Neuronpedia

    INDEX
    Explanations

    phrases related to streamlining processes or systems

    oai_token-act-pair · gpt-3.5-turbo

    references to telecommunications or communication technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburg
    -0.82
    rum
    -0.81
    CVE
    -0.77
    rament
    -0.75
     Seym
    -0.75
    iddles
    -0.75
    undai
    -0.75
    ilton
    -0.74
    etsy
    -0.74
     mathemat
    -0.72
    POSITIVE LOGITS
    backer
    1.34
    lined
    0.83
    lihood
    0.80
    breaks
    0.80
    aments
    0.74
    phrine
    0.72
    break
    0.71
    wise
    0.71
    lines
    0.70
    ups
    0.68
    Act Density 0.026%

    No Known Activations