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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to percentages and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appropriately
    -0.61
     tremend
    -0.56
    ulet
    -0.56
    sole
    -0.55
    accompanied
    -0.55
    igible
    -0.55
    saf
    -0.53
    querque
    -0.53
    ufact
    -0.53
    rament
    -0.52
    POSITIVE LOGITS
    307
    0.76
    331
    0.68
    653
    0.67
    806
    0.66
    659
    0.66
    309
    0.66
    305
    0.65
    MJ
    0.65
    377
    0.64
    604
    0.64
    Act Density 0.292%

    No Known Activations