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

    Neuronpedia

    INDEX
    Explanations

    phrases related to introducing or warning about upcoming information

    oai_token-act-pair · gpt-3.5-turbo

    introductory phrases that indicate planning or preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pier
    -0.62
    ãĥĩ
    -0.62
    oad
    -0.62
     diam
    -0.59
     outp
    -0.58
    omet
    -0.57
    aden
    -0.57
    vell
    -0.56
    iday
    -0.56
     succeeding
    -0.55
    POSITIVE LOGITS
     briefly
    0.89
     Explain
    0.84
     acknowledge
    0.84
     acquaint
    0.83
     introduce
    0.83
     recognize
    0.82
     clarify
    0.82
     remember
    0.81
     remind
    0.81
     let
    0.81
    Act Density 0.184%

    No Known Activations