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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with legal or regulatory content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utto
    -0.18
    ´Ī
    -0.16
    dux
    -0.15
     rig
    -0.15
    ardi
    -0.15
    mps
    -0.14
    arkan
    -0.14
    ekte
    -0.14
    iler
    -0.14
    .bz
    -0.14
    POSITIVE LOGITS
    tone
    0.15
    aty
    0.15
    none
    0.15
    ologna
    0.15
    iques
    0.14
    stan
    0.14
     Katy
    0.14
    efined
    0.14
    NONE
    0.14
    å®
    0.14
    Act Density 0.022%

    No Known Activations