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

    Neuronpedia

    INDEX
    Explanations

    comparisons, particularly those referencing competitive matchups

    oai_token-act-pair · gpt-3.5-turbo

    comparative structures and phrases detailing competition or rivalry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ).[
    -0.77
    ".[
    -0.62
    ."[
    -0.61
     moreover
    -0.54
     Slate
    -0.53
     lobbying
    -0.49
     nonetheless
    -0.48
     SetTextColor
    -0.47
    versely
    -0.47
     sshd
    -0.47
    POSITIVE LOGITS
     Replay
    0.63
    ?'
    0.62
    ?",
    0.59
     ;)
    0.59
     ',
    0.56
    aturday
    0.53
    iru
    0.53
     \'
    0.52
     */
    0.52
     haha
    0.51
    Act Density 2.970%

    No Known Activations