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

    Neuronpedia

    INDEX
    Explanations

    comparisons or evaluations of similarities or differences between individuals

    oai_token-act-pair · gpt-3.5-turbo

    comparisons of abilities, characteristics, or statuses among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antic
    -0.77
     postponed
    -0.73
     Accessed
    -0.69
    ãĤ¡
    -0.69
     reuse
    -0.68
     mediation
    -0.68
     avoidance
    -0.66
     stabilization
    -0.65
    iHUD
    -0.63
    nect
    -0.63
    POSITIVE LOGITS
    average
    1.04
     others
    0.96
     anybody
    0.94
     peers
    0.92
     everyone
    0.90
     everybody
    0.88
     himself
    0.87
     anyone
    0.87
     colleagues
    0.85
     fellow
    0.82
    Act Density 0.226%

    No Known Activations