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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sequence or continuation of text

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "Of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     partName
    -0.78
    daq
    -0.65
     sew
    -0.65
     corners
    -0.64
    "}],"
    -0.64
     pled
    -0.62
    taboola
    -0.62
    ocene
    -0.62
     epid
    -0.61
    2200
    -0.61
    POSITIVE LOGITS
     course
    1.10
    ortunately
    0.86
    course
    0.81
    obin
    0.81
     Lies
    0.80
    rontal
    0.77
     sorts
    0.75
    onso
    0.75
    elia
    0.75
     Course
    0.71
    Act Density 0.080%

    No Known Activations