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

    Neuronpedia

    INDEX
    Explanations

    instances of positive encouragement or support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chter
    -0.15
    ianne
    -0.15
     tud
    -0.14
     feder
    -0.14
     federation
    -0.14
    orus
    -0.14
    омеÑĢ
    -0.14
    ообÑĢаз
    -0.14
    à¥ĥत
    -0.13
    à¸Ļà¸Ļ
    -0.13
    POSITIVE LOGITS
    ebo
    0.17
    708
    0.17
    arer
    0.15
    rens
    0.15
    raq
    0.15
    aku
    0.14
    žÃŃ
    0.14
    éĩĩ
    0.14
    -focus
    0.14
    709
    0.14
    Act Density 0.001%

    No Known Activations