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

    Neuronpedia

    INDEX
    Explanations

    phrases related to destruction and harmful actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndPassword
    -0.17
    otti
    -0.15
    Ä±ÅŁ
    -0.15
    NotNull
    -0.15
    iras
    -0.15
    ereal
    -0.14
    sembly
    -0.14
    .truth
    -0.14
    edo
    -0.14
    cot
    -0.14
    POSITIVE LOGITS
    urgeon
    0.18
    ienne
    0.16
    essel
    0.15
    ablish
    0.14
     phá
    0.14
    lake
    0.14
    exels
    0.14
    itters
    0.13
    aley
    0.13
    ITTER
    0.13
    Act Density 0.037%

    No Known Activations