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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong opinions or descriptions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    arettes
    -0.74
     Clouds
    -0.73
    neath
    -0.71
    cius
    -0.70
     Engineers
    -0.68
    DERR
    -0.68
    urtles
    -0.67
    pps
    -0.66
     Roses
    -0.65
     Pigs
    -0.65
    POSITIVE LOGITS
     arrangement
    1.03
     endeavor
    0.93
     ploy
    0.90
     thing
    0.88
     tale
    0.85
     initiative
    0.85
     conco
    0.84
     phenomenon
    0.84
     maneuver
    0.83
     tactic
    0.83
    Act Density 0.336%

    No Known Activations