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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forgetting and memory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    styleType
    -0.71
     genomen
    -0.68
    ThroughAttribute
    -0.67
     resourceCulture
    -0.66
     iArr
    -0.64
    PreferredItem
    -0.64
    Население
    -0.61
     snippetHide
    -0.59
    makeText
    -0.58
    Collegamenti
    -0.58
    POSITIVE LOGITS
     forget
    2.18
     forgetting
    2.08
     forgets
    2.04
     forgot
    1.96
     forgotten
    1.94
     FORGET
    1.89
    forget
    1.85
     Forget
    1.81
     Forgotten
    1.67
    Forget
    1.64
    Act Density 0.034%

    No Known Activations