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

    Neuronpedia

    INDEX
    Explanations

    words related to temperature and temperament

    oai_token-act-pair · gpt-3.5-turbo

    terms related to temperature and temperament

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.68
     Lans
    -0.68
    IJ
    -0.66
     NX
    -0.66
     HHS
    -0.66
    ISS
    -0.65
     Doe
    -0.64
     Annotations
    -0.64
    rd
    -0.63
    location
    -0.63
    POSITIVE LOGITS
     tant
    1.29
    amental
    1.24
    aments
    1.13
     temper
    1.01
    mental
    0.95
     Temper
    0.92
    atures
    0.91
    pit
    0.85
    ate
    0.82
    ance
    0.81
    Act Density 0.015%

    No Known Activations