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

    Neuronpedia

    INDEX
    Explanations

    references to manual processes or operations, particularly in a technical or procedural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IATION
    -0.45
     witnessed
    -0.44
     witness
    -0.40
    ########.
    -0.40
     witnessing
    -0.40
     Witness
    -0.39
     Weather
    -0.39
     weather
    -0.39
     Investigation
    -0.36
    uegos
    -0.36
    POSITIVE LOGITS
     climate
    0.84
     Climate
    0.81
    Climate
    0.81
     CLIMATE
    0.77
    climate
    0.76
    Manual
    0.64
     Paused
    0.61
     manual
    0.61
     klima
    0.61
    manual
    0.58
    Act Density 0.030%

    No Known Activations