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

    Neuronpedia

    INDEX
    Explanations

    expressions related to forgetting or memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    forgetting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.47
     pleaſure
    -0.47
     knex
    -0.46
    InputBorder
    -0.45
    ModelAdmin
    -0.39
     sumo
    -0.39
    Spoljašnje
    -0.38
    -0.38
    eun
    -0.38
     juſ
    -0.38
    POSITIVE LOGITS
     forget
    1.50
     forgetting
    1.42
    forget
    1.38
     forgets
    1.38
     forgotten
    1.30
     forgot
    1.25
     Forget
    1.23
     esquecer
    1.23
    forgotten
    1.21
     FORGET
    1.21
    Act Density 0.009%

    No Known Activations