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

    Neuronpedia

    INDEX
    Explanations

    words related to supervision, oversight, or management

    oai_token-act-pair · gpt-3.5-turbo

    terms related to supervision and accomplices in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bed
    -0.70
     gif
    -0.69
    DEN
    -0.68
    lights
    -0.68
    REDACTED
    -0.66
    ARB
    -0.65
    cloth
    -0.64
    boat
    -0.64
     Shed
    -0.63
     rad
    -0.63
    POSITIVE LOGITS
    ising
    1.86
    ises
    1.85
    ise
    1.73
    isons
    1.68
    ised
    1.65
    isions
    1.65
    ices
    1.59
    isance
    1.52
    isers
    1.52
    isable
    1.51
    Act Density 0.077%

    No Known Activations