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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of removing or deleting something

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

    Removal or deletion

    np_acts-logits-general · gemini-2.0-flash

    removing unwanted items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.59
     tantôt
    -0.58
    textTheme
    -0.57
    prepareStatement
    -0.54
     đảo
    -0.53
    orsese
    -0.51
    wnątrz
    -0.50
    󠁿
    -0.50
     Walkover
    -0.49
     تضيفلها
    -0.47
    POSITIVE LOGITS
     unnecessary
    1.17
     unwanted
    1.11
     superfluous
    1.08
     excess
    1.01
     extraneous
    0.95
     redundant
    0.95
     offending
    0.90
    excess
    0.88
    Excess
    0.83
     pesky
    0.83
    Act Density 0.467%

    No Known Activations