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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific roles or positions within organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with services and roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.90
    ãĥķãĤ©
    -0.78
    Ext
    -0.74
    OX
    -0.69
     Tropical
    -0.67
     arrang
    -0.66
     mathemat
    -0.66
     Ext
    -0.65
    Measure
    -0.65
    ãĤ¦ãĤ¹
    -0.64
    POSITIVE LOGITS
    mans
    0.89
     persons
    0.88
     woman
    0.86
     person
    0.86
    tarians
    0.85
     cohort
    0.84
    lander
    0.84
     warriors
    0.83
     comrades
    0.83
     Females
    0.82
    Act Density 0.565%

    No Known Activations