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

    Neuronpedia

    INDEX
    Explanations

    phrases related to configurations or arrangements

    oai_token-act-pair · gpt-3.5-turbo

    references to various configurations or arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.82
    inals
    -0.72
    orie
    -0.71
    thood
    -0.71
     Ago
    -0.69
    pha
    -0.69
    onso
    -0.69
    emi
    -0.67
    ollow
    -0.65
    ibli
    -0.65
    POSITIVE LOGITS
     setup
    0.89
    eering
    0.89
     setups
    0.87
    eers
    0.83
    setup
    0.75
     Setup
    0.74
     regimen
    0.70
     procedure
    0.69
     configurations
    0.69
    mate
    0.68
    Act Density 0.010%

    No Known Activations