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

    Neuronpedia

    INDEX
    Explanations

    numerical values, terms related to games and sports, and technical descriptions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    eatures
    -0.79
     Azerb
    -0.77
    Ô
    -0.74
     immedi
    -0.68
     suspic
    -0.67
     redund
    -0.67
     Tanz
    -0.66
     qualitative
    -0.65
     Euph
    -0.65
     instantaneous
    -0.64
    POSITIVE LOGITS
    horn
    0.73
    mods
    0.73
     Fest
    0.70
    eton
    0.67
     boxes
    0.66
    hound
    0.66
    moon
    0.65
    enary
    0.65
    iaries
    0.64
    obook
    0.64
    Act Density 11.632%

    No Known Activations