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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of floating, especially in a physical context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.82
    heimer
    -0.73
    xx
    -0.70
    okers
    -0.69
     à¨
    -0.67
    mins
    -0.65
    anasia
    -0.65
    nect
    -0.65
    ENA
    -0.63
    tained
    -0.61
    POSITIVE LOGITS
    flo
    1.00
    plane
    0.86
     pond
    0.83
    pole
    0.81
     floating
    0.75
    assets
    0.73
    uten
    0.73
    planes
    0.71
     Floating
    0.70
    aval
    0.70
    Act Density 0.025%

    No Known Activations