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

    Neuronpedia

    INDEX
    Explanations

    patterns of unusual character sequences or non-standard encoded text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    keepers
    -0.16
    zn
    -0.15
    keeper
    -0.15
    keeping
    -0.15
    fully
    -0.15
    quake
    -0.14
    kea
    -0.14
    fy
    -0.14
    tracted
    -0.13
    fo
    -0.13
    POSITIVE LOGITS
    s
    0.23
    o
    0.18
    umer
    0.16
    i
    0.15
    e
    0.15
    l
    0.14
    iders
    0.14
    t
    0.14
    oise
    0.14
    Äįel
    0.14
    Act Density 0.077%

    No Known Activations