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

    Neuronpedia

    INDEX
    Explanations

    phrases related to endings or closures

    oai_token-act-pair · gpt-3.5-turbo

    references to closures or endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.68
    insky
    -0.66
    fman
    -0.66
     toget
    -0.65
    enne
    -0.65
    PRO
    -0.64
    clair
    -0.63
    olen
    -0.63
     ideally
    -0.63
     glean
    -0.63
    POSITIVE LOGITS
     prematurely
    0.91
     altogether
    0.88
     due
    0.85
     :(
    0.81
     Reason
    0.79
     citing
    0.78
    due
    0.75
    ecause
    0.75
     disgrace
    0.73
     abruptly
    0.71
    Act Density 0.684%

    No Known Activations