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

    Neuronpedia

    INDEX
    Explanations

    phrases related to individual actions and interactions in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¿ãĥ«
    -0.17
    andon
    -0.16
    orld
    -0.16
    arn
    -0.15
    nees
    -0.15
    slaught
    -0.15
    ɵ
    -0.15
    afe
    -0.14
    english
    -0.14
    igar
    -0.14
    POSITIVE LOGITS
    hest
    0.15
     Orchard
    0.15
    ÑĢÑİ
    0.14
     Vie
    0.14
    į¼
    0.13
    849
    0.13
     supern
    0.13
     Ministers
    0.13
     Mess
    0.13
    еÑĤÑĥ
    0.13
    Act Density 0.425%

    No Known Activations