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

    Neuronpedia

    INDEX
    Explanations

    the word "single" associated with a numerical value

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    akings
    -0.91
    apons
    -0.84
    Downloadha
    -0.83
    ooks
    -0.81
    raints
    -0.75
    ours
    -0.75
    olas
    -0.74
    UFF
    -0.71
    iquette
    -0.69
    acements
    -0.69
    POSITIVE LOGITS
    handedly
    1.18
     digit
    1.06
    ton
    1.03
     person
    0.99
     piece
    0.99
     molecule
    0.90
     digits
    0.90
     minute
    0.89
     minded
    0.88
     batch
    0.87
    Act Density 0.022%

    No Known Activations