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

    Neuronpedia

    INDEX
    Explanations

    keywords related to medical procedures or technical processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surgery and medical or procedural processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.73
    ALSE
    -0.64
    teness
    -0.64
    hao
    -0.64
     curiosity
    -0.62
    auc
    -0.60
    amiya
    -0.60
    mberg
    -0.59
     unden
    -0.59
    blank
    -0.59
    POSITIVE LOGITS
     fared
    1.36
     interacts
    1.17
     compares
    1.10
     differs
    1.10
     relates
    1.07
     affects
    1.06
     stacks
    1.05
     relate
    1.03
     unfolded
    1.03
     reacted
    1.02
    Act Density 0.233%

    No Known Activations