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

    Neuronpedia

    INDEX
    Explanations

    proper nouns such as names of locations, organizations, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their related context in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oooooooooooooooo
    -0.72
    zos
    -0.65
     blo
    -0.64
    (*
    -0.63
    arton
    -0.62
    choes
    -0.61
    blers
    -0.60
    yip
    -0.60
    hang
    -0.59
    cdn
    -0.59
    POSITIVE LOGITS
     constitu
    0.80
     ILCS
    0.71
     Frames
    0.69
     Committees
    0.67
     COUNTY
    0.67
     Tonight
    0.66
     âĵĺ
    0.62
     Latest
    0.62
     Polk
    0.62
     MEN
    0.61
    Act Density 0.055%

    No Known Activations