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

    Neuronpedia

    INDEX
    Explanations

    words related to emotional control or composure

    oai_token-act-pair · gpt-3.5-turbo

    instances and variations of the word "stoic" or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaru
    -0.85
    orge
    -0.78
    puter
    -0.77
    ptin
    -0.75
    enez
    -0.74
    edu
    -0.74
    owship
    -0.72
    wered
    -0.72
    auna
    -0.72
    Medic
    -0.71
    POSITIVE LOGITS
     Vaugh
    0.80
    Ħ¢
    0.75
     CST
    0.71
    cold
    0.67
     Bees
    0.66
    WT
    0.66
    yss
    0.64
     fitt
    0.64
     Weber
    0.63
    ����
    0.63
    Act Density 0.072%

    No Known Activations