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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases associated with formal statements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ponge
    -0.15
    ëĤľ
    -0.15
     primitive
    -0.14
    agua
    -0.14
    ovny
    -0.14
    inker
    -0.14
    awi
    -0.14
    itar
    -0.14
     éĥ
    -0.13
    ahat
    -0.13
    POSITIVE LOGITS
    جÛĮ
    0.17
    acy
    0.16
    ously
    0.16
     Redistributions
    0.16
    ering
    0.15
    IDL
    0.15
    erer
    0.15
     egret
    0.14
    aries
    0.14
    STM
    0.14
    Act Density 0.005%

    No Known Activations