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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate recurring or recent time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yet
    -0.15
    bbing
    -0.15
    kening
    -0.15
    arts
    -0.15
    ogan
    -0.14
    ky
    -0.14
    aware
    -0.14
    ERICA
    -0.14
    ãĥ£
    -0.13
    uner
    -0.13
    POSITIVE LOGITS
     few
    0.39
     couple
    0.29
    few
    0.25
     decade
    0.24
    Few
    0.23
    åĩł
    0.23
     Few
    0.22
     several
    0.22
     year
    0.21
     beberapa
    0.20
    Act Density 0.048%

    No Known Activations