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

    Neuronpedia

    INDEX
    Explanations

    words related to significant events or important topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant societal and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Osiris
    -0.73
     Jenkins
    -0.70
    tnc
    -0.67
    debian
    -0.67
    displayText
    -0.67
     Laf
    -0.66
    erey
    -0.66
    tiny
    -0.65
     Santos
    -0.65
    reys
    -0.64
    POSITIVE LOGITS
     imaginable
    0.97
     ever
    0.88
     accomplishment
    0.81
     achie
    0.77
     EVER
    0.77
     offender
    0.75
     achievement
    0.75
     artery
    0.74
     subsequ
    0.73
     lineback
    0.72
    Act Density 0.288%

    No Known Activations