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

    Neuronpedia

    INDEX
    Explanations

    references to "beacons" and related words in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zhou
    -0.16
    plet
    -0.15
    olvers
    -0.15
     Gould
    -0.15
    bred
    -0.15
    -Origin
    -0.14
     vin
    -0.14
    gger
    -0.14
    yun
    -0.13
    noc
    -0.13
    POSITIVE LOGITS
    rist
    0.15
    lesc
    0.15
     Rouge
    0.14
    ãĥ£
    0.14
    licht
    0.14
    æĿŁ
    0.14
     Vale
    0.14
    otal
    0.14
    -setting
    0.14
    semb
    0.13
    Act Density 0.004%

    No Known Activations