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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positivity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.88
     Brilliant
    -0.73
    HAEL
    -0.73
    opsy
    -0.70
     Mellon
    -0.68
    wine
    -0.68
    tracks
    -0.64
     spo
    -0.63
     Lucia
    -0.63
    Leod
    -0.63
    POSITIVE LOGITS
    itional
    1.60
    itions
    1.43
    itivity
    1.31
    itionally
    1.22
    idon
    1.16
    itor
    1.15
    ited
    1.09
    itors
    1.07
    itiveness
    1.06
    icion
    1.06
    Act Density 0.061%

    No Known Activations