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

    Neuronpedia

    INDEX
    Explanations

    locations and dates

    oai_token-act-pair · gpt-3.5-turbo

    specific locations and geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subjective
    -0.58
     bias
    -0.57
     negativity
    -0.56
     MOT
    -0.55
     biography
    -0.54
     pessim
    -0.53
    lihood
    -0.53
     gratification
    -0.52
     Expand
    -0.52
     clutter
    -0.52
    POSITIVE LOGITS
    quartered
    0.80
    zona
    0.73
    ĪĴ
    0.70
    region
    0.69
    outhern
    0.68
    opolis
    0.68
    outheast
    0.67
    itol
    0.65
    orthern
    0.64
    abouts
    0.64
    Act Density 1.533%

    No Known Activations