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

    Neuronpedia

    INDEX
    Explanations

    words related to endings, conclusions, or finality

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "closure"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nis
    -0.86
    inen
    -0.72
    yah
    -0.72
    yton
    -0.72
    olf
    -0.71
    orum
    -0.71
    icist
    -0.70
    arat
    -0.70
    kaya
    -0.70
    uld
    -0.70
    POSITIVE LOGITS
     shroud
    0.85
     closures
    0.77
    closure
    0.77
    Closure
    0.75
     lid
    0.73
     shutter
    0.73
     curtains
    0.72
    ãĤ¬
    0.72
     postponed
    0.72
     closure
    0.68
    Act Density 0.021%

    No Known Activations