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

    Neuronpedia

    INDEX
    Explanations

    thresholds or limits

    oai_token-act-pair · gpt-3.5-turbo

    references to various thresholds in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ateur
    -0.78
    obbies
    -0.71
    oir
    -0.69
    adoes
    -0.68
    ulf
    -0.66
    ocate
    -0.66
    arus
    -0.65
    irit
    -0.62
    enza
    -0.62
    rongh
    -0.61
    POSITIVE LOGITS
     threshold
    0.95
     thresholds
    0.93
     clearance
    0.88
     cutoff
    0.86
    posts
    0.85
     criteria
    0.77
    =$
    0.77
     hurdle
    0.77
     requirement
    0.77
    stones
    0.75
    Act Density 0.058%

    No Known Activations