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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames or handles

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric strings and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavi
    -0.86
    âĸ¬
    -0.75
     withd
    -0.72
    CLASSIFIED
    -0.72
     resil
    -0.71
    WAYS
    -0.70
    insula
    -0.67
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.66
     carbohyd
    -0.64
    BALL
    -0.64
    POSITIVE LOGITS
    zn
    0.92
    jj
    0.92
    zx
    0.90
    0
    0.88
    ifi
    0.88
    gallery
    0.87
    kk
    0.87
    qq
    0.86
    fb
    0.86
    df
    0.86
    Act Density 0.060%

    No Known Activations