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

    Neuronpedia

    INDEX
    Explanations

    references to human involvement in processes and manual efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Printer
    -0.16
    lemetry
    -0.15
    akis
    -0.15
    uset
    -0.15
    ucci
    -0.15
    ekl
    -0.14
    adius
    -0.14
    Wunused
    -0.14
    akeup
    -0.14
     secrecy
    -0.13
    POSITIVE LOGITS
     manual
    0.40
     manually
    0.37
     Manual
    0.32
     MANUAL
    0.30
    manual
    0.29
    Manual
    0.29
    /manual
    0.27
    _manual
    0.26
    .manual
    0.25
     human
    0.21
    Act Density 0.134%

    No Known Activations