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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing quotes or indicating a source of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence or actions of groups or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    runtime
    -0.72
     Alone
    -0.69
    livion
    -0.67
     Himself
    -0.67
     Carbuncle
    -0.67
    ĸļ
    -0.66
    Quantity
    -0.65
     haha
    -0.65
     ;)
    -0.65
    ë
    -0.64
    POSITIVE LOGITS
     observers
    1.31
     commenters
    1.27
     analysts
    1.26
     commentators
    1.25
     critics
    1.15
     lawmakers
    1.11
     experts
    1.10
     prominent
    1.03
     economists
    1.02
     indications
    1.02
    Act Density 0.211%

    No Known Activations