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

    Neuronpedia

    INDEX
    Explanations

    technical instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    references to parts or phases of a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brand
    -0.85
     abroad
    -0.74
     internationally
    -0.74
    United
    -0.73
     Cosponsors
    -0.69
    American
    -0.68
    iberal
    -0.66
     Thomson
    -0.66
    soever
    -0.66
    quartered
    -0.65
    POSITIVE LOGITS
     onwards
    0.81
     filler
    0.79
     countdown
    0.79
     prol
    0.79
     completion
    0.75
     Verse
    0.74
     climax
    0.73
     finishes
    0.73
    rontal
    0.72
     stages
    0.72
    Act Density 0.643%

    No Known Activations