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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "forget" and its variations, indicating a focus on themes of memory and forgetting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    styleType
    -0.85
     通販
    -0.77
     iArr
    -0.75
    MigrationBuilder
    -0.74
    CodedInputStream
    -0.72
     genomen
    -0.71
    PreferredItem
    -0.71
    IsContent
    -0.71
    TintMode
    -0.70
    évaluateur
    -0.68
    POSITIVE LOGITS
     forget
    1.69
     forgetting
    1.61
     forgets
    1.55
     forgotten
    1.54
     FORGET
    1.52
     forgot
    1.48
     Forget
    1.42
    forget
    1.39
     Forgotten
    1.36
    Forget
    1.29
    Act Density 0.033%

    No Known Activations