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

    Neuronpedia

    INDEX
    Explanations

    mentions of possible actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential future actions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.77
    ants
    -0.73
    iments
    -0.71
    items
    -0.69
    ense
    -0.68
    facts
    -0.68
    inel
    -0.67
    ographs
    -0.66
    grounds
    -0.65
    Statistics
    -0.65
    POSITIVE LOGITS
     possible
    1.16
     comeback
    1.04
     reunion
    0.97
     showdown
    0.97
     future
    0.96
     rematch
    0.95
     potential
    0.95
     sequel
    0.91
    venge
    0.90
     revival
    0.89
    Act Density 0.288%

    No Known Activations