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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the conclusion or termination of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onth
    -0.15
    eut
    -0.15
    ész
    -0.14
    buz
    -0.14
     Griff
    -0.14
     opinion
    -0.14
     alternative
    -0.14
    ca
    -0.14
    612
    -0.13
     оÑĤп
    -0.13
    POSITIVE LOGITS
     AB
    0.16
     Sleep
    0.15
    illard
    0.14
    HttpRequest
    0.14
     sleep
    0.14
    Sleep
    0.14
    aly
    0.14
    ιÏĥÏĦή
    0.14
    ishment
    0.13
    VRT
    0.13
    Act Density 0.057%

    No Known Activations