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

    Neuronpedia

    INDEX
    Explanations

    references to "manual" processes or controls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.50
    visející
    -0.46
    PreferredItem
    -0.44
     ře
    -0.44
    untungan
    -0.43
    testify
    -0.43
    })`
    -0.43
     suela
    -0.42
    InitVars
    -0.42
    ℏ
    -0.41
    POSITIVE LOGITS
     manual
    0.98
     manually
    0.78
     manufactured
    0.77
    manual
    0.76
     manufacture
    0.73
    Manual
    0.71
     Manual
    0.69
    Manufactured
    0.64
     manuals
    0.63
     MANUAL
    0.63
    Act Density 0.255%

    No Known Activations