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

    Neuronpedia

    INDEX
    Explanations

    instances of forgetting and memory-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awtextra
    -0.56
     pleaſure
    -0.46
     itſelf
    -0.44
    Carrière
    -0.43
    wiſe
    -0.42
    Pranala
    -0.42
    rshire
    -0.42
    Aos
    -0.40
    AOS
    -0.40
     userDao
    -0.39
    POSITIVE LOGITS
     forget
    1.80
     forgot
    1.64
     forgets
    1.63
     forgetting
    1.59
     forgotten
    1.58
    forget
    1.55
     Forget
    1.51
     FORGET
    1.45
    forgotten
    1.38
    Forget
    1.38
    Act Density 0.160%

    No Known Activations