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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to offsets and alignment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mie
    -0.16
    place
    -0.16
    uset
    -0.15
     poh
    -0.15
    kö
    -0.15
    keh
    -0.14
    istic
    -0.14
    pest
    -0.14
    istically
    -0.14
    aug
    -0.14
    POSITIVE LOGITS
    ting
    0.30
    ing
    0.25
    ted
    0.23
    edImage
    0.19
    edReader
    0.18
    0.17
    .BASELINE
    0.17
    ters
    0.17
    omers
    0.16
    ÑĪиÑģÑĮ
    0.16
    Act Density 0.060%

    No Known Activations