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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names, specifically related to different locations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    words related to government or agency references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.71
     hail
    -0.69
     selves
    -0.64
     caution
    -0.62
     cones
    -0.62
     detrim
    -0.61
     enterprise
    -0.61
     entrants
    -0.60
     boundaries
    -0.59
     lengths
    -0.58
    POSITIVE LOGITS
    wered
    0.98
    imity
    0.93
    heim
    0.89
    otropic
    0.88
    omaly
    0.86
    aldo
    0.84
    obic
    0.83
    imov
    0.83
    mia
    0.81
    oly
    0.80
    Act Density 0.070%

    No Known Activations