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

    Neuronpedia

    INDEX
    Explanations

    terms related to accidents and incidents, particularly those involving negative consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ninger
    -0.16
     Laurent
    -0.16
     Rat
    -0.14
    Ł
    -0.14
    isko
    -0.14
    ney
    -0.14
    usra
    -0.14
    леÑĤ
    -0.14
    ycin
    -0.14
    yer
    -0.14
    POSITIVE LOGITS
    aro
    0.18
    posal
    0.18
    ì±
    0.17
    ÑģÑĤе
    0.16
    uncated
    0.15
    bil
    0.15
    ventus
    0.14
    ugi
    0.14
    jr
    0.14
    andes
    0.14
    Act Density 0.005%

    No Known Activations