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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "come" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    habi
    -0.17
    laps
    -0.16
    kiye
    -0.16
    пÑĢ
    -0.15
    .onClick
    -0.15
    ÙĦÛĮسÛĮ
    -0.14
    lob
    -0.14
    oval
    -0.14
    ends
    -0.14
    bolt
    -0.14
    POSITIVE LOGITS
    PHA
    0.16
    Ķ
    0.15
    ülü
    0.14
    TypeEnum
    0.14
    STM
    0.14
    abyrin
    0.14
    UNET
    0.14
    Stride
    0.14
    iyi
    0.13
    ülen
    0.13
    Act Density 0.015%

    No Known Activations