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

    Neuronpedia

    INDEX
    Explanations

    direct address or references to an individual in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éd
    -0.16
    ocy
    -0.15
    @qq
    -0.14
     fucked
    -0.14
    orgh
    -0.14
    ustry
    -0.14
    inus
    -0.14
    grily
    -0.14
    ynchronously
    -0.14
    ergus
    -0.14
    POSITIVE LOGITS
     sound
    0.26
     obviously
    0.21
     two
    0.19
     sir
    0.19
     said
    0.19
     ok
    0.19
     mentioned
    0.19
     ever
    0.18
     mean
    0.18
     poor
    0.17
    Act Density 0.117%

    No Known Activations