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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of large financial values

    oai_token-act-pair · gpt-3.5-turbo

    phrases and descriptions related to chaotic or violent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forts
    -0.78
     freed
    -0.72
     Abbey
    -0.71
     Duchess
    -0.70
    yrights
    -0.70
     lux
    -0.69
     princess
    -0.69
    uild
    -0.68
     immortality
    -0.67
     heirs
    -0.67
    POSITIVE LOGITS
     escalation
    1.19
     escalate
    1.06
     incidents
    1.04
     occurring
    1.04
     occurrences
    1.00
     escalated
    0.99
     perpetrated
    0.97
     escalating
    0.96
    £ı
    0.92
     hysteria
    0.89
    Act Density 1.108%

    No Known Activations