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

    Neuronpedia

    INDEX
    Explanations

    mentions of existing things or situations

    oai_token-act-pair · gpt-3.5-turbo

    the word "existing" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ousse
    -0.94
    alion
    -0.83
    ÃŃa
    -0.78
    ertodd
    -0.77
    rea
    -0.76
    owitz
    -0.75
    romeda
    -0.75
    olic
    -0.74
    oche
    -0.73
    ueller
    -0.73
    POSITIVE LOGITS
    existing
    0.79
     existing
    0.78
     liabilities
    0.76
     arrangements
    0.74
    foundland
    0.73
     tenant
    0.71
    ITIES
    0.69
    entials
    0.69
     relationships
    0.69
     generations
    0.68
    Act Density 0.038%

    No Known Activations