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

    Neuronpedia

    INDEX
    Explanations

    informational narratives or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to news stories and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iolet
    -0.73
    inia
    -0.70
    inav
    -0.65
    udget
    -0.62
    abbling
    -0.62
    hire
    -0.60
    imble
    -0.58
    entimes
    -0.58
    ankind
    -0.58
    razil
    -0.57
    POSITIVE LOGITS
    liest
    1.07
    iest
    1.01
    same
    0.90
     anew
    0.88
     himself
    0.86
     correctly
    0.83
     equivalent
    0.80
     anonymously
    0.79
     behind
    0.77
    wrong
    0.76
    Act Density 0.394%

    No Known Activations