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

    Neuronpedia

    INDEX
    Explanations

    phrases related to project timelines and extensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confisc
    -0.16
    acf
    -0.15
     flatt
    -0.15
    rottle
    -0.14
    otp
    -0.14
    nox
    -0.14
    832
    -0.14
    kud
    -0.14
    switch
    -0.13
    acular
    -0.13
    POSITIVE LOGITS
     extension
    0.44
     extensions
    0.44
     extend
    0.39
     Extensions
    0.38
     Extension
    0.38
     Extend
    0.37
    extension
    0.37
    -extension
    0.36
    extend
    0.36
    extensions
    0.36
    Act Density 0.122%

    No Known Activations