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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or describe various aspects or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igh
    -0.17
     Harding
    -0.16
    éĢ¸
    -0.16
    /cgi
    -0.15
    '])){
    -0.15
    otas
    -0.14
    furt
    -0.14
    loff
    -0.14
    à¥ĭश
    -0.14
    inand
    -0.14
    POSITIVE LOGITS
     lid
    0.30
     dent
    0.23
     wedge
    0.21
     smile
    0.21
    lid
    0.20
     price
    0.19
     dam
    0.18
     Lid
    0.18
     halt
    0.18
     brakes
    0.18
    Act Density 0.050%

    No Known Activations