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

    Neuronpedia

    INDEX
    Explanations

    information related to military or official-related terms, potentially referencing testing or business jets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.89
    姫
    -0.79
    ãĥīãĥ©
    -0.76
    gers
    -0.75
    creen
    -0.73
    ²¾
    -0.73
    ãĥĥãĥĪ
    -0.68
    ãĥ³ãĤ¸
    -0.67
    ãĥ¼ãĥ³
    -0.66
    pmwiki
    -0.66
    POSITIVE LOGITS
    arrass
    1.25
    odied
    1.16
    edded
    1.13
    assies
    1.05
    argo
    1.04
    assy
    1.03
    attled
    1.02
    odies
    0.99
    olicy
    0.98
    ead
    0.88
    Act Density 0.017%

    No Known Activations