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

    Neuronpedia

    INDEX
    Explanations

    terms related to dramatic content and themes in television and film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boro
    -0.18
    istrovstvÃŃ
    -0.17
     latter
    -0.16
    è¦
    -0.15
    ieg
    -0.15
    ilver
    -0.14
    tplib
    -0.14
    oo
    -0.14
    пÑĤом
    -0.14
    entially
    -0.14
    POSITIVE LOGITS
    íĭ±
    0.23
     queen
    0.21
    atic
    0.21
     queens
    0.20
    queen
    0.19
     llama
    0.19
    /com
    0.18
    atur
    0.18
    -document
    0.18
    /action
    0.17
    Act Density 0.019%

    No Known Activations