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

    Neuronpedia

    INDEX
    Explanations

    questions or statements that introduce a topic or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iren
    -0.16
    ough
    -0.15
    inson
    -0.14
    975
    -0.14
     Hooks
    -0.14
    agli
    -0.14
    esta
    -0.14
     vid
    -0.14
    stery
    -0.14
     mu
    -0.14
    POSITIVE LOGITS
    onet
    0.15
    оÑħ
    0.15
    RC
    0.15
    ypass
    0.14
    oslav
    0.14
    erton
    0.14
    еÑĨÑĤ
    0.14
    uj
    0.14
    nger
    0.14
    CTL
    0.13
    Act Density 0.001%

    No Known Activations