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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate events, actions, and occurrences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eroon
    -0.17
    oleÄį
    -0.16
    ossa
    -0.16
     Seconds
    -0.15
     Pins
    -0.15
    lix
    -0.15
    chner
    -0.15
    agan
    -0.15
    Corner
    -0.14
    vider
    -0.14
    POSITIVE LOGITS
     spill
    0.16
     leak
    0.16
     priorit
    0.15
     le
    0.14
    apor
    0.14
     boys
    0.14
     fashion
    0.14
    .pivot
    0.14
     Leak
    0.14
     Boy
    0.13
    Act Density 0.027%

    No Known Activations