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

    Neuronpedia

    INDEX
    Explanations

    phrases related to travel and exploration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exclusivity or being first to know about something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equivalents
    -0.65
    xual
    -0.64
    None
    -0.60
     embodiments
    -0.60
    illary
    -0.58
    Father
    -0.56
    cond
    -0.56
    Delivery
    -0.56
    Fine
    -0.56
    anism
    -0.56
    POSITIVE LOGITS
     subscriber
    0.68
    ribune
    0.67
     KNOW
    0.67
     voic
    0.65
    served
    0.64
    ixel
    0.64
     alerted
    0.64
    efeated
    0.61
    elight
    0.60
     Saga
    0.60
    Act Density 0.045%

    No Known Activations