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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the origin or source of something

    oai_token-act-pair · gpt-3.5-turbo

    references to origins or sources of people, objects, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     attrition
    -0.66
    İĭ
    -0.59
    mens
    -0.58
     "+
    -0.57
     Pend
    -0.57
    osi
    -0.57
     Ships
    -0.57
    =-=-
    -0.57
    midt
    -0.56
     Closed
    -0.56
    POSITIVE LOGITS
    abouts
    0.80
    achi
    0.70
    ?'
    0.69
    lins
    0.68
    alian
    0.67
     spiritually
    0.64
    atel
    0.64
    nings
    0.64
    ?'"
    0.63
    igating
    0.63
    Act Density 0.172%

    No Known Activations