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

    Neuronpedia

    INDEX
    Explanations

    numerical values that are part of data or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or identifiers related to data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.82
    think
    -0.82
    holder
    -0.76
    estine
    -0.73
    ously
    -0.71
    blind
    -0.67
    athing
    -0.65
    pper
    -0.65
    eting
    -0.65
    anke
    -0.65
    POSITIVE LOGITS
     ILCS
    0.99
    é¾
    0.92
    mph
    0.86
     dB
    0.81
    374
    0.78
    503
    0.77
    20439
    0.77
    508
    0.76
    803
    0.73
    40
    0.73
    Act Density 0.032%

    No Known Activations