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

    Neuronpedia

    INDEX
    Explanations

    language related to personal experiences and emotional reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    borg
    -0.16
    ivery
    -0.16
     themselves
    -0.15
     phen
    -0.14
    sla
    -0.14
    hog
    -0.14
    ELLOW
    -0.13
    374
    -0.13
    .bundle
    -0.13
    Ãłn
    -0.13
    POSITIVE LOGITS
    βε
    0.17
    yt
    0.16
    èĮĥ
    0.14
    леменÑĤ
    0.14
    utz
    0.14
    ichel
    0.13
     VOID
    0.13
    inion
    0.13
     Hastings
    0.13
    ovan
    0.13
    Act Density 0.398%

    No Known Activations