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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'of' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "firsts" or initial experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    contin
    -0.80
     unfocusedRange
    -0.75
    GRE
    -0.71
     abound
    -0.71
    complex
    -0.69
    RELATED
    -0.67
    sports
    -0.67
    prov
    -0.65
    ãĥĥ
    -0.65
    replace
    -0.63
    POSITIVE LOGITS
     introdu
    0.75
     whiff
    0.74
     Alto
    0.73
     EVER
    0.72
     ever
    0.68
     glimpse
    0.68
     incarnation
    0.65
     imaginable
    0.65
     ascent
    0.63
    iaz
    0.63
    Act Density 0.453%

    No Known Activations