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

    Neuronpedia

    INDEX
    Explanations

    phrases related to empowerment and taking control of a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to empowerment and overcoming adversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Definitely
    -0.71
    ciating
    -0.71
    isSpecialOrderable
    -0.70
     Ready
    -0.70
    arella
    -0.70
    éŃĶ
    -0.69
     surprisingly
    -0.67
    itatively
    -0.67
    umably
    -0.67
    inally
    -0.67
    POSITIVE LOGITS
     overshadow
    1.05
     interfere
    1.02
     distract
    1.01
     tarn
    0.99
     detract
    0.96
     intimidate
    0.94
     deceive
    0.91
     stagn
    0.90
     contam
    0.90
     mislead
    0.89
    Act Density 0.176%

    No Known Activations