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

    Neuronpedia

    INDEX
    Explanations

    the word "of" occurring in phrases where it precedes a descriptive term or concept

    oai_token-act-pair · gpt-3.5-turbo

    phrases or instances that reference different "versions" of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urers
    -0.97
     teasp
    -0.80
    ering
    -0.79
    ered
    -0.75
    resy
    -0.72
    rings
    -0.71
    erity
    -0.68
    phasis
    -0.68
    rences
    -0.67
    ern
    -0.66
    POSITIVE LOGITS
    reality
    0.69
    thood
    0.67
    ĨĴ
    0.65
     Impossible
    0.62
     events
    0.61
     life
    0.60
     history
    0.59
     theirs
    0.59
    skill
    0.58
    orthodox
    0.57
    Act Density 0.084%

    No Known Activations