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

    Neuronpedia

    INDEX
    Explanations

    references to specific days or dates

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to significant days or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.83
    negie
    -0.78
    itars
    -0.78
    icide
    -0.76
    emale
    -0.73
    icides
    -0.72
    bourg
    -0.71
    umbn
    -0.70
    cientious
    -0.69
    icultural
    -0.69
    POSITIVE LOGITS
    dream
    1.47
    care
    0.94
    light
    0.93
    lights
    0.87
    trip
    0.84
    break
    0.83
    flower
    0.83
    TON
    0.81
    lighting
    0.79
    walker
    0.77
    Act Density 0.064%

    No Known Activations