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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irty
    -0.15
    io
    -0.15
    ollapsed
    -0.15
     infring
    -0.14
    rnd
    -0.14
    lad
    -0.14
    otel
    -0.14
    ibox
    -0.14
    fw
    -0.13
    èIJ½
    -0.13
    POSITIVE LOGITS
     Indexed
    0.16
    uby
    0.15
    /jav
    0.14
    nad
    0.14
    Hal
    0.14
    zano
    0.13
    isson
    0.13
    ì²
    0.13
    izu
    0.13
    olet
    0.13
    Act Density 0.131%

    No Known Activations