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

    Neuronpedia

    INDEX
    Explanations

    words related to marking or emphasizing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mark" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     substantially
    -0.71
     mishand
    -0.69
     moderately
    -0.69
     surviv
    -0.68
     agon
    -0.67
     VIDE
    -0.67
     decomp
    -0.67
     positively
    -0.66
     mono
    -0.66
    ADS
    -0.65
    POSITIVE LOGITS
    marks
    1.59
    mark
    1.57
    emark
    1.15
    furt
    1.08
    manship
    1.08
    ertodd
    1.00
    eters
    0.97
    marked
    0.93
    uments
    0.90
    hof
    0.87
    Act Density 0.008%

    No Known Activations