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

    Neuronpedia

    INDEX
    Explanations

    expressions of forgetfulness or memory lapses

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

    forgotten actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cuevas
    -0.37
     bluzka
    -0.35
    UserDto
    -0.35
     stanow
    -0.35
     damska
    -0.34
     zeer
    -0.33
    SafeAreaView
    -0.32
     financeira
    -0.32
    oore
    -0.32
    リーン
    -0.32
    POSITIVE LOGITS
     forgot
    0.84
    rungsseite
    0.75
    forgot
    0.73
     Forgot
    0.73
    Forgot
    0.71
     tartalomajánló
    0.67
    (!__
    0.66
     forgotten
    0.65
     forgets
    0.65
     linkovi
    0.63
    Act Density 0.013%

    No Known Activations