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

    Neuronpedia

    INDEX
    Explanations

    words related to job activities or job conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to employment and job conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oxide
    -0.82
    perse
    -0.78
    phrine
    -0.78
    cean
    -0.76
    vous
    -0.76
    DragonMagazine
    -0.71
    angel
    -0.69
    powder
    -0.68
    vae
    -0.68
    clave
    -0.67
    POSITIVE LOGITS
    ĻĤ
    0.78
     vocational
    0.71
    ij士
    0.70
     apprentices
    0.68
    ikuman
    0.66
     Herbert
    0.65
     rentals
    0.64
     Tate
    0.64
     obedience
    0.63
     waivers
    0.61
    Act Density 0.419%

    No Known Activations