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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uet
    -0.16
    .pixel
    -0.15
    ced
    -0.15
    leon
    -0.14
    cela
    -0.14
    hte
    -0.14
    wich
    -0.14
    entials
    -0.13
    ELSE
    -0.13
    null
    -0.13
    POSITIVE LOGITS
    çIJ³
    0.15
    تش
    0.14
    /Area
    0.14
    iversite
    0.14
    chter
    0.14
     Kramer
    0.14
    iner
    0.14
    egl
    0.14
    uth
    0.14
    auty
    0.13
    Act Density 0.010%

    No Known Activations