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

    Neuronpedia

    INDEX
    Explanations

    phrases referencing official departments or offices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    話
    -0.16
    OLUM
    -0.15
    że
    -0.15
    immer
    -0.15
    pow
    -0.15
    cret
    -0.14
    hazi
    -0.14
    wise
    -0.14
    -wise
    -0.14
    amation
    -0.14
    POSITIVE LOGITS
    ãĥ³ãĥIJ
    0.15
    tica
    0.15
    estro
    0.14
    λεκ
    0.14
    Reviewed
    0.14
    orias
    0.14
    utsch
    0.14
     Plenty
    0.14
     LGPL
    0.14
    ailles
    0.13
    Act Density 0.005%

    No Known Activations