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

    Neuronpedia

    INDEX
    Explanations

    phrases related to full-time positions or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to full-time employment or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artisan
    -0.78
    ramid
    -0.76
    riks
    -0.75
    haar
    -0.75
    alach
    -0.74
    haps
    -0.70
    ortium
    -0.69
    inia
    -0.67
    lain
    -0.67
     scattered
    -0.66
    POSITIVE LOGITS
    frames
    1.05
    time
    0.99
    borne
    0.97
    frame
    0.94
    zone
    0.83
    glass
    0.79
     Bucc
    0.78
     inacc
    0.75
    llor
    0.74
    Machine
    0.74
    Act Density 0.015%

    No Known Activations