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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    segments of text that are empty or contain no significant content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mares
    -0.65
    pill
    -0.60
    secut
    -0.59
    ologies
    -0.57
     bush
    -0.56
    oking
    -0.56
    esthes
    -0.55
    abre
    -0.55
    ively
    -0.54
    orship
    -0.54
    POSITIVE LOGITS
    vernment
    1.12
    iants
    0.90
    roups
    0.89
    busters
    0.83
    raphic
    0.81
    irlfriend
    0.80
    omez
    0.78
    reens
    0.77
    stones
    0.76
    glers
    0.75
    Act Density 0.246%

    No Known Activations