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

    Neuronpedia

    INDEX
    Explanations

    words related to people or locations

    oai_token-act-pair · gpt-3.5-turbo

    words related to health conditions and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.81
    e
    -0.72
    eve
    -0.70
    ed
    -0.69
     Ukrain
    -0.64
    ful
    -0.63
    £ı
    -0.63
    fax
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.62
     unfocusedRange
    -0.60
    POSITIVE LOGITS
    asso
    0.92
    asts
    0.89
    atform
    0.86
    olicy
    0.81
    uggage
    0.81
    merce
    0.78
    ocalypse
    0.78
    azine
    0.75
    arks
    0.74
    ocaly
    0.72
    Act Density 0.045%

    No Known Activations