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

    Neuronpedia

    INDEX
    Explanations

    technical specifications or details

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to specifications and technical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hound
    -1.00
    lift
    -0.88
    etheless
    -0.78
    kus
    -0.78
    winter
    -0.74
    ilee
    -0.69
    hurst
    -0.69
     Sheen
    -0.68
    zees
    -0.67
    kers
    -0.67
    POSITIVE LOGITS
     specifications
    1.24
     Specifications
    1.01
    imens
    0.99
     specs
    0.98
    imen
    0.85
     specification
    0.83
    ifications
    0.81
    eters
    0.78
     specifies
    0.75
    Spec
    0.73
    Act Density 0.046%

    No Known Activations