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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software development and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and compatibility details related to software and devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hust
    -0.78
    prison
    -0.77
    illin
    -0.77
     burgl
    -0.75
     gul
    -0.74
    ickr
    -0.74
     chilling
    -0.73
    reprene
    -0.72
     calming
    -0.72
     calmly
    -0.72
    POSITIVE LOGITS
     compatibility
    1.75
     interoper
    1.60
     compatible
    1.59
     Compatibility
    1.46
    compatible
    1.40
     supported
    1.34
     incompatible
    1.33
    Supported
    1.31
     versions
    1.26
     Supported
    1.26
    Act Density 0.452%

    No Known Activations