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 temperamental qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.77
    gom
    -0.76
    location
    -0.67
    ÅĤ
    -0.66
     Lans
    -0.66
    km
    -0.66
    Jul
    -0.65
    rd
    -0.65
    nz
    -0.64
     NX
    -0.64
    POSITIVE LOGITS
     tant
    1.30
    amental
    1.19
    aments
    1.18
     temper
    1.07
     Temper
    0.96
    pit
    0.89
    mental
    0.86
    atures
    0.82
    ament
    0.82
    uate
    0.82
    Act Density 0.009%

    No Known Activations