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

    Neuronpedia

    INDEX
    Explanations

    phrases related to institutional issues or settings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to institutional structures and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    person
    -0.84
    woman
    -0.82
    glass
    -0.81
    women
    -0.80
    model
    -0.79
    models
    -0.79
    lihood
    -0.77
    gl
    -0.71
    gur
    -0.70
    vich
    -0.70
    POSITIVE LOGITS
    ized
    0.92
    iary
    0.89
     inertia
    0.85
    ised
    0.83
    iation
    0.83
    aneously
    0.82
    iated
    0.79
     divid
    0.74
    aneous
    0.74
    izes
    0.72
    Act Density 0.170%

    No Known Activations