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

    Neuronpedia

    INDEX
    Explanations

    references to war and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estruction
    -0.17
    itsu
    -0.16
    oo
    -0.15
    žila
    -0.15
    ilver
    -0.15
    วรร
    -0.15
    elsing
    -0.14
    owo
    -0.14
    erver
    -0.14
    ungeons
    -0.14
    POSITIVE LOGITS
    lord
    0.17
    zone
    0.16
    lords
    0.15
    æľ«
    0.15
    lock
    0.14
     against
    0.14
    LAB
    0.14
    ìĿį
    0.14
    TokenType
    0.14
    -ending
    0.14
    Act Density 0.046%

    No Known Activations