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

    Neuronpedia

    INDEX
    Explanations

    references to movement or change in position, particularly related to human activity

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and conjunctions indicating relationships and positions within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matically
    -0.73
    ]}
    -0.64
    OUND
    -0.59
    `,
    -0.58
     tong
    -0.57
     ageing
    -0.57
     =================================
    -0.57
     wise
    -0.56
    initialized
    -0.56
     clusters
    -0.54
    POSITIVE LOGITS
    Balt
    0.94
    cock
    0.69
    lean
    0.66
    ãĥĥãĥĪ
    0.66
    onian
    0.66
    pat
    0.63
    rescent
    0.63
    qus
    0.63
     Bulg
    0.63
    rir
    0.62
    Act Density 1.259%

    No Known Activations