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

    Neuronpedia

    INDEX
    Explanations

    discourse about the implications and seriousness of violence and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĮĦ
    -0.13
     Ñģвоими
    -0.13
    ader
    -0.12
    adero
    -0.12
    μεν
    -0.12
    ierung
    -0.12
    adies
    -0.12
    iem
    -0.12
     Afterwards
    -0.12
    Due
    -0.12
    POSITIVE LOGITS
     blanket
    0.20
     few
    0.20
     I
    0.20
     Taken
    0.19
     absent
    0.19
    Taken
    0.18
     taken
    0.17
     such
    0.17
     plenty
    0.17
     context
    0.17
    Act Density 0.380%

    No Known Activations