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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "forgot."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "forgot" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     attractive
    -0.70
     impact
    -0.64
    ocative
    -0.64
     competitive
    -0.64
     robust
    -0.64
     ÂŃ
    -0.62
     tough
    -0.62
     aggressive
    -0.61
     range
    -0.61
     striking
    -0.60
    POSITIVE LOGITS
     forgot
    3.79
     forgetting
    1.74
     forg
    1.42
     forget
    1.37
     hid
    1.28
     forgotten
    1.26
    got
    1.25
     didnt
    1.25
     stole
    1.17
     froze
    1.17
    Act Density 0.015%

    No Known Activations