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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events happening over a significant period of time

    oai_token-act-pair · gpt-3.5-turbo

    elements related to personal choices and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggles
    -0.63
     Adds
    -0.63
     Recent
    -0.60
    Ô
    -0.55
     Prepare
    -0.55
    Adds
    -0.54
    */
    -0.52
     WATCH
    -0.52
    Update
    -0.50
    zens
    -0.50
    POSITIVE LOGITS
     mattered
    1.43
     lacked
    1.43
     resembled
    1.40
     was
    1.39
     seemed
    1.38
     depended
    1.37
     wasn
    1.34
     tended
    1.33
     belonged
    1.33
     had
    1.30
    Act Density 1.535%

    No Known Activations