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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" indicating temporal references or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cope
    -0.18
    krv
    -0.15
    isu
    -0.15
    HEMA
    -0.15
    αιδ
    -0.15
    tic
    -0.15
    enties
    -0.14
    jes
    -0.14
    friend
    -0.14
    odem
    -0.14
    POSITIVE LOGITS
    abouts
    0.18
    soever
    0.17
    EVER
    0.16
    /if
    0.14
    ims
    0.14
    zych
    0.14
    upon
    0.13
     superf
    0.13
    eca
    0.13
    ÅĻÃŃž
    0.13
    Act Density 0.142%

    No Known Activations