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

    Neuronpedia

    INDEX
    Explanations

    mentions of explosives and bomb-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leon
    -0.17
    'Ñı
    -0.15
    vis
    -0.15
    icum
    -0.14
    dere
    -0.14
    ioso
    -0.14
    ulo
    -0.14
    ợi
    -0.14
     tails
    -0.14
    ãģ¨ãģĨ
    -0.14
    POSITIVE LOGITS
    alette
    0.17
     Explos
    0.15
    arial
    0.15
    stretch
    0.14
     Heard
    0.14
    culus
    0.14
    oden
    0.14
    .expand
    0.13
    epend
    0.13
    sole
    0.13
    Act Density 0.150%

    No Known Activations