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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific styles or fashion choices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    emi
    -0.81
    wright
    -0.72
    ora
    -0.70
    arte
    -0.69
    pec
    -0.67
    ipedia
    -0.66
    pedia
    -0.66
    ma
    -0.65
    frey
    -0.64
    omen
    -0.63
    POSITIVE LOGITS
    lihood
    0.70
     punishments
    0.65
     proportions
    0.64
     executions
    0.63
     precision
    0.63
     immersion
    0.62
     insanity
    0.62
     landslide
    0.61
     correctional
    0.61
     killers
    0.60
    Act Density 9.612%

    No Known Activations