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

    Neuronpedia

    INDEX
    Explanations

    commands or actions that require immediate attention or response

    oai_token-act-pair · gpt-3.5-turbo

    references to prompts or prompting actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Extrem
    -0.72
     Sect
    -0.67
    apest
    -0.67
    IRD
    -0.65
    gdala
    -0.65
    amia
    -0.62
     GEAR
    -0.62
    dx
    -0.62
    UGH
    -0.62
    mbuds
    -0.61
    POSITIVE LOGITS
     prompt
    1.34
    itude
    1.01
     prompts
    1.00
     Prompt
    0.91
    ously
    0.88
    tale
    0.85
     succession
    0.75
    ings
    0.75
    inently
    0.73
    taining
    0.73
    Act Density 0.006%

    No Known Activations