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

    Neuronpedia

    INDEX
    Explanations

    phrases related to closures or shutdowns

    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
    -0.79
    inen
    -0.79
    kaya
    -0.78
    reme
    -0.76
    uld
    -0.75
    icist
    -0.73
    yah
    -0.71
    eva
    -0.70
    Iv
    -0.68
    llular
    -0.68
    POSITIVE LOGITS
    ãĤ¬
    0.78
     lid
    0.77
     closures
    0.77
    Closure
    0.76
     shroud
    0.76
    closure
    0.74
     radius
    0.70
     moratorium
    0.69
     closure
    0.67
     margin
    0.66
    Act Density 0.017%

    No Known Activations