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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive outcomes or success in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñħи
    -0.18
    enton
    -0.17
    eda
    -0.15
     Winn
    -0.15
    eniable
    -0.15
    ourt
    -0.15
    leta
    -0.15
     hence
    -0.15
    lej
    -0.14
    enda
    -0.14
    POSITIVE LOGITS
     because
    0.35
     porque
    0.30
    because
    0.30
    Because
    0.27
     Because
    0.27
     поÑĤомÑĥ
    0.24
     karena
    0.24
     perché
    0.23
     omdat
    0.22
     parce
    0.22
    Act Density 0.214%

    No Known Activations