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

    Neuronpedia

    INDEX
    Explanations

    connections between characters and their relationships or actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ington
    -0.14
     Duck
    -0.14
     kennen
    -0.14
    wards
    -0.14
    assis
    -0.14
    QUENCY
    -0.14
    illy
    -0.13
    ãģĿãĤĮãģ¯
    -0.13
    bon
    -0.13
    #echo
    -0.13
    POSITIVE LOGITS
     sich
    0.28
     zich
    0.23
     herself
    0.23
     themselves
    0.20
     itself
    0.20
     himself
    0.20
     oneself
    0.19
     Himself
    0.18
     Ø®ÙĪد
    0.17
    æk
    0.16
    Act Density 0.068%

    No Known Activations