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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve relationships between different components or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igg
    -0.17
    inou
    -0.14
    OrUpdate
    -0.14
    isku
    -0.14
    osaic
    -0.14
    ková
    -0.13
    AndPassword
    -0.13
    wake
    -0.13
    fak
    -0.13
     createState
    -0.13
    POSITIVE LOGITS
     no
    0.17
     lots
    0.17
     plenty
    0.15
    olan
    0.15
     spur
    0.14
     some
    0.14
     added
    0.14
    ä¸Ķ
    0.13
     Hole
    0.13
    enan
    0.13
    Act Density 0.071%

    No Known Activations