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

    Neuronpedia

    INDEX
    Explanations

    references to letters and written correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yan
    -0.19
    yum
    -0.17
    yon
    -0.16
    sale
    -0.16
    ertain
    -0.16
    eline
    -0.16
    vier
    -0.15
    emaker
    -0.15
    illet
    -0.15
    erty
    -0.15
    POSITIVE LOGITS
    press
    0.27
    ìĹ´
    0.19
    atura
    0.19
    red
    0.18
    head
    0.18
    winner
    0.17
    boxed
    0.17
    -spacing
    0.17
    .docs
    0.16
    olem
    0.15
    Act Density 0.022%

    No Known Activations