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

    Neuronpedia

    INDEX
    Explanations

    Strong action words like "Shut" or "give" in the text

    oai_token-act-pair · gpt-3.5-turbo

    actions and processes related to movement or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illian
    -0.77
    ritic
    -0.71
    ici
    -0.71
    illi
    -0.69
    ichen
    -0.67
     Physicians
    -0.67
    IFA
    -0.67
     Feder
    -0.66
    ori
    -0.65
    rito
    -0.64
    POSITIVE LOGITS
    up
    1.57
     up
    1.42
    ups
    1.36
    Up
    1.35
    UP
    1.23
     Up
    1.23
     ups
    1.22
     UP
    1.15
    down
    1.01
     ashore
    0.99
    Act Density 0.126%

    No Known Activations