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

    Neuronpedia

    INDEX
    Explanations

    words related to entities such as organizations, countries, and institutions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizations, institutions, and collective groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ultimate
    -0.72
    iasis
    -0.69
    oux
    -0.67
    ifest
    -0.66
    ipeg
    -0.62
    odox
    -0.62
    shows
    -0.61
    atever
    -0.59
    ilee
    -0.58
    izoph
    -0.58
    POSITIVE LOGITS
     vying
    0.84
    folk
    0.82
     adopting
    0.80
     have
    0.79
     scrambled
    0.78
     allocate
    0.76
    hare
    0.75
     implementing
    0.75
     employing
    0.75
     adopt
    0.75
    Act Density 0.292%

    No Known Activations