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

    Neuronpedia

    INDEX
    Explanations

    instructions or actions related to manual processes

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "manually" in the context of tasks or actions performed by hand rather than through automation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.77
    addons
    -0.73
     Kerry
    -0.72
    our
    -0.70
    rug
    -0.70
    riots
    -0.70
     Neighbor
    -0.68
    soon
    -0.67
     Millennium
    -0.67
     Framework
    -0.66
    POSITIVE LOGITS
     induct
    0.83
     overcl
    0.82
     calibr
    0.81
     override
    0.80
     operated
    0.78
     programmed
    0.78
     manually
    0.76
     audition
    0.76
     configured
    0.75
     bleed
    0.75
    Act Density 0.010%

    No Known Activations