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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate detailed descriptions or explanations of concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fts
    -0.15
    eding
    -0.14
    ree
    -0.14
    u
    -0.14
    iste
    -0.14
    IBILITY
    -0.14
    >
    -0.14
    cket
    -0.14
     provision
    -0.14
    isp
    -0.14
    POSITIVE LOGITS
     elsewhere
    0.20
    ALSE
    0.19
     below
    0.18
     HERE
    0.17
     вÑĭÑĪе
    0.16
     ниже
    0.16
    .Framework
    0.16
    OptionPane
    0.15
     above
    0.15
    _consts
    0.15
    Act Density 0.129%

    No Known Activations