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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses that suggest relationships, qualities, or characteristics of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venta
    -0.17
    idth
    -0.15
     CONTRIBUTORS
    -0.15
    pell
    -0.14
    atta
    -0.14
    inding
    -0.13
    iele
    -0.13
     Representation
    -0.13
    iltr
    -0.13
    sey
    -0.13
    POSITIVE LOGITS
    alon
    0.15
    verb
    0.15
     extreme
    0.15
     Extreme
    0.15
    decess
    0.15
    ãĥ¼ãĥĬ
    0.14
    dÃŃ
    0.14
    ajan
    0.14
     boh
    0.14
    éĢļãĤĬ
    0.14
    Act Density 0.005%

    No Known Activations