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

    Neuronpedia

    INDEX
    Explanations

    technology-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    indicators of the end of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arsen
    -0.65
     Charm
    -0.63
     certainty
    -0.61
     McH
    -0.60
     cooks
    -0.59
     ages
    -0.58
     corrid
    -0.57
     heel
    -0.57
     Applicant
    -0.56
     whisk
    -0.56
    POSITIVE LOGITS
    tenance
    0.96
    coins
    0.81
    oft
    0.81
    research
    0.81
    sand
    0.81
    fen
    0.80
    dit
    0.79
    rising
    0.78
    nexus
    0.76
    obj
    0.75
    Act Density 0.262%

    No Known Activations