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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" indicating a focus on specific clauses or details in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucken
    -0.20
    zdy
    -0.16
    129
    -0.16
    razione
    -0.16
    [assembly
    -0.16
    PACKAGE
    -0.15
    enez
    -0.15
    iou
    -0.15
    inkle
    -0.14
    .Areas
    -0.14
    POSITIVE LOGITS
    [:]
    0.15
    inho
    0.15
    ifix
    0.14
    è¯ij
    0.14
    eping
    0.14
    rien
    0.14
    arbon
    0.14
    _PREVIEW
    0.14
    .tim
    0.13
    tea
    0.13
    Act Density 0.041%

    No Known Activations