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

    Neuronpedia

    INDEX
    Explanations

    words related to legal permissions and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aura
    -0.14
    edeki
    -0.14
    æijĺè¦ģ
    -0.14
    ÅĻeb
    -0.13
    enne
    -0.13
    he
    -0.13
    ÑĥÑĩа
    -0.13
    دÙħ
    -0.13
    ãģ«ãģ¨
    -0.13
    oji
    -0.13
    POSITIVE LOGITS
     any
    0.16
    ANY
    0.16
     allowed
    0.15
     touching
    0.15
    ordin
    0.15
     certain
    0.15
    ayscale
    0.15
     unless
    0.15
     ANY
    0.15
    inho
    0.15
    Act Density 0.145%

    No Known Activations