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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forgetting, ignoring, or dismissing memories and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     voici
    -0.54
     katze
    -0.53
    Personendaten
    -0.52
     мәкалә
    -0.51
    estra
    -0.51
     الرخصة
    -0.51
    падает
    -0.50
     hObject
    -0.49
     fú
    -0.49
     Sauerstoff
    -0.48
    POSITIVE LOGITS
     pretend
    0.80
     forget
    0.77
     ignore
    0.77
     Ignore
    0.76
     ignor
    0.75
     ignored
    0.71
     ignorance
    0.68
     ignoring
    0.68
     ignores
    0.67
     forgets
    0.67
    Act Density 0.258%

    No Known Activations