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

    Neuronpedia

    INDEX
    Explanations

    instances of specific symbols or unique characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udi
    -0.17
    åłĤ
    -0.15
    inker
    -0.15
    aeper
    -0.15
    anyak
    -0.14
    ddit
    -0.14
    ãĥ¼ãĥ«ãĥī
    -0.14
    eming
    -0.14
    eor
    -0.13
    _then
    -0.13
    POSITIVE LOGITS
     apart
    0.20
     once
    0.20
     beyond
    0.20
     besides
    0.19
     aside
    0.19
     versus
    0.19
     vs
    0.18
     away
    0.17
     Reviewed
    0.17
     therefore
    0.17
    Act Density 0.005%

    No Known Activations