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

    Neuronpedia

    INDEX
    Explanations

    verbs related to action or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to packaging, breaking, and controlling processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rock
    -0.77
    fur
    -0.74
    odon
    -0.69
    eli
    -0.69
    pmwiki
    -0.68
    hai
    -0.68
    Virgin
    -0.67
    win
    -0.66
    habi
    -0.65
    wolves
    -0.65
    POSITIVE LOGITS
     theirs
    1.13
     hers
    0.91
     anything
    0.88
     them
    0.86
     yours
    0.85
     everything
    0.85
     something
    0.76
     ours
    0.76
     another
    0.74
     arbitrary
    0.73
    Act Density 0.984%

    No Known Activations