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

    Neuronpedia

    INDEX
    Explanations

    instances of ellipsis (...) at the end of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or incomplete thoughts suggesting a pause or continuation in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     empath
    -0.85
     purse
    -0.77
     attest
    -0.77
     cradle
    -0.76
     outl
    -0.73
     sympath
    -0.72
     symp
    -0.71
     staggered
    -0.71
     indemn
    -0.70
     mobilized
    -0.70
    POSITIVE LOGITS
     âĢİ
    1.09
     Appears
    1.01
    BUT
    0.90
    Bah
    0.89
    BACK
    0.84
    DOWN
    0.84
    @@
    0.84
    ↵Âł
    0.83
     Specifications
    0.83
     =================================
    0.83
    Act Density 0.022%

    No Known Activations