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

    Neuronpedia

    INDEX
    Explanations

    relationships and conflicts between characters in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erot
    -0.14
    wner
    -0.14
    leftright
    -0.13
    %f
    -0.13
    æģ
    -0.13
    pping
    -0.13
    LIK
    -0.13
     podrob
    -0.13
    gers
    -0.13
    åIJįçĦ¡ãģĹãģķãĤĵ
    -0.13
    POSITIVE LOGITS
     Jr
    0.24
    's
    0.23
    nie
    0.22
     who
    0.22
    ’s
    0.20
     whom
    0.20
    -chan
    0.20
     himself
    0.19
    -sama
    0.19
     Sr
    0.19
    Act Density 0.329%

    No Known Activations