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

    Neuronpedia

    INDEX
    Explanations

    words related to fear and terror

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fta
    -1.03
     fign
    -1.01
     ftu
    -1.00
     NOO
    -0.97
     poff
    -0.96
     fup
    -0.91
     proprement
    -0.91
     paff
    -0.91
     unil
    -0.91
     aen
    -0.90
    POSITIVE LOGITS
     fear
    1.00
     afraid
    0.96
     fearing
    0.93
     fearful
    0.88
    fraid
    0.84
     fears
    0.81
     feared
    0.81
     scared
    0.80
    Fear
    0.77
     Fear
    0.77
    Act Density 0.553%

    No Known Activations