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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to achievements or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to sports performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tempt
    -0.63
     cautioned
    -0.63
     urge
    -0.63
    ulner
    -0.62
     blame
    -0.62
    itiz
    -0.61
     lure
    -0.61
     stigma
    -0.61
    apego
    -0.61
     downside
    -0.60
    POSITIVE LOGITS
     increments
    0.94
     nutshell
    0.87
     guise
    0.86
     manner
    0.86
     msec
    0.85
     milliseconds
    0.85
     fashion
    0.84
     batches
    0.77
     seconds
    0.77
     minutes
    0.77
    Act Density 0.134%

    No Known Activations