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

    Neuronpedia

    INDEX
    Explanations

    instances where tasks are done manually in contrast to electronically

    oai_token-act-pair · gpt-3.5-turbo

    references to manual processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fell
    -0.67
     Matters
    -0.65
     prosperity
    -0.64
     Said
    -0.63
    SPONSORED
    -0.63
    ory
    -0.62
     belief
    -0.62
    pires
    -0.62
    fits
    -0.59
     epit
    -0.59
    POSITIVE LOGITS
     manually
    3.77
     dynamically
    1.53
     electronically
    1.42
     statically
    1.34
     individually
    1.33
     digitally
    1.28
     automate
    1.26
     blindly
    1.26
     automatically
    1.25
     artificially
    1.24
    Act Density 0.019%

    No Known Activations