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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to communication or connection

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to interaction and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zn
    -0.78
    peria
    -0.75
    ft
    -0.71
    prus
    -0.71
    GE
    -0.69
    ciples
    -0.69
    cott
    -0.68
    aft
    -0.67
    haps
    -0.67
    zik
    -0.66
    POSITIVE LOGITS
     interactions
    0.97
    ivity
    0.95
    uate
    0.88
     interaction
    0.87
    ually
    0.87
    iences
    0.85
    ively
    0.84
    ivating
    0.81
    ioned
    0.79
    halla
    0.78
    Act Density 0.019%

    No Known Activations