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

    Neuronpedia

    INDEX
    Explanations

    terms related to individuals or groups involved in decision-making or law-making processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to creators or producers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UR
    -0.72
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
    ãĥ¥
    -0.61
    ention
    -0.61
    HHHH
    -0.61
     curs
    -0.59
     connection
    -0.58
     physical
    -0.58
     Samp
    -0.56
     fluent
    -0.55
    POSITIVE LOGITS
    makers
    4.47
    maker
    4.20
    making
    2.70
     makers
    2.25
     maker
    2.13
    Maker
    1.93
     Maker
    1.65
    builders
    1.28
    holder
    1.28
    builder
    1.17
    Act Density 0.014%

    No Known Activations