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

    Neuronpedia

    INDEX
    Explanations

    words related to various professions and industries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various roles or groups of people (e.g., clients, workers, users, students)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TX
    -0.73
    SPONSORED
    -0.72
     hers
    -0.69
     ..."
    -0.67
    shapeshifter
    -0.66
    âĪĴ
    -0.65
    cv
    -0.65
    TEXTURE
    -0.65
    MR
    -0.63
     theirs
    -0.63
    POSITIVE LOGITS
    hip
    1.01
    wana
    1.00
    ource
    0.93
    haw
    0.89
    cript
    0.86
    hips
    0.85
    afety
    0.84
    pace
    0.82
    ettings
    0.81
     Picks
    0.81
    Act Density 0.176%

    No Known Activations