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

    Neuronpedia

    INDEX
    Explanations

    numeric figures or data descriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.74
    cyclopedia
    -0.70
    00000
    -0.68
    artney
    -0.67
    izabeth
    -0.66
    emies
    -0.65
    VICE
    -0.64
    ription
    -0.64
    lopp
    -0.64
     Sussex
    -0.63
    POSITIVE LOGITS
     skating
    0.99
     prominently
    0.94
    heads
    0.92
    head
    0.84
    book
    0.73
    table
    0.71
    hatt
    0.71
     Rasmussen
    0.69
    sonian
    0.68
    inery
    0.68
    Act Density 0.726%

    No Known Activations