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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to technology and engineering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to management and organizational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.58
    âķIJâķIJ
    -0.58
    yss
    -0.56
    GAN
    -0.56
    ENGTH
    -0.54
    ARR
    -0.54
    DATA
    -0.52
    ITNESS
    -0.50
    PUT
    -0.49
    FI
    -0.48
    POSITIVE LOGITS
    hips
    1.07
    hops
    0.97
    etter
    0.92
    hip
    0.91
    etting
    0.87
    afety
    0.84
    uits
    0.84
    uggest
    0.81
    chool
    0.81
    paces
    0.81
    Act Density 1.046%

    No Known Activations