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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate knowledge or awareness about specific topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rug
    -0.16
    EATURE
    -0.15
    iggins
    -0.14
    endent
    -0.14
    ÑĢд
    -0.14
    ullan
    -0.13
    elez
    -0.13
    alance
    -0.13
    eature
    -0.13
    ismo
    -0.13
    POSITIVE LOGITS
    .lu
    0.15
    WAYS
    0.14
    üb
    0.14
    zman
    0.14
     dangers
    0.14
    places
    0.14
    akra
    0.13
    lys
    0.13
    ardi
    0.13
     repr
    0.13
    Act Density 0.118%

    No Known Activations