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

    Neuronpedia

    INDEX
    Explanations

    sentences concluding an argument or expressing finality

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.83
    ensen
    -0.72
    ãĥĭ
    -0.71
     Meier
    -0.71
    mens
    -0.64
    itol
    -0.64
     Ducks
    -0.64
    isphere
    -0.61
    inals
    -0.60
    nown
    -0.58
    POSITIVE LOGITS
    Interstitial
    1.14
    Cause
    0.94
     ',
    0.93
    taboola
    0.90
    cause
    0.83
    Mech
    0.81
    -'
    0.80
     '.
    0.77
     ('
    0.76
    tis
    0.72
    Act Density 0.068%

    No Known Activations