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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and common transitional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    757
    -0.15
    /DD
    -0.14
    аÑĤков
    -0.14
    iller
    -0.13
     simply
    -0.13
    ooks
    -0.13
     Unidos
    -0.13
    ÎĿ
    -0.13
    ảy
    -0.13
    createForm
    -0.13
    POSITIVE LOGITS
     Pulitzer
    0.15
    rew
    0.15
    ulla
    0.15
    éli
    0.15
     Thom
    0.15
    _initializer
    0.14
    gran
    0.14
    046
    0.14
    052
    0.14
    ToF
    0.14
    Act Density 0.241%

    No Known Activations