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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technical terms and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    references to technical or legal terms related to digital systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kers
    -0.72
    Reviewer
    -0.71
    giving
    -0.70
     Carnegie
    -0.69
    hunt
    -0.68
    olulu
    -0.66
    igun
    -0.66
    ship
    -0.65
    kamp
    -0.65
    ker
    -0.65
    POSITIVE LOGITS
    AIN
    0.91
     DOM
    0.86
    aine
    0.84
    inant
    0.83
    OME
    0.78
    inating
    0.77
    NAT
    0.76
    ANT
    0.76
    APH
    0.76
    RA
    0.76
    Act Density 0.014%

    No Known Activations