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

    Neuronpedia

    INDEX
    Explanations

    words related to code or technical specifications, in particular focusing on items that are able to be manipulated or modified

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate capability or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erva
    -0.79
    ffic
    -0.73
    itect
    -0.72
    ega
    -0.69
    umat
    -0.69
    acha
    -0.69
    urer
    -0.68
    OTO
    -0.66
    ORS
    -0.65
    akedown
    -0.65
    POSITIVE LOGITS
    lihood
    0.80
    bodied
    0.69
    pedia
    0.69
    atable
    0.68
    bage
    0.67
     Leafs
    0.66
     guid
    0.65
    pox
    0.65
     bowel
    0.64
     lapse
    0.64
    Act Density 0.095%

    No Known Activations