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

    Neuronpedia

    INDEX
    Explanations

    connections and transitions in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickers
    -0.17
    tingham
    -0.15
    ulus
    -0.15
    /on
    -0.15
    ashboard
    -0.15
    tah
    -0.14
    emez
    -0.14
     Homeland
    -0.13
     Heg
    -0.13
    istor
    -0.13
    POSITIVE LOGITS
     itself
    0.28
     herself
    0.25
     zich
    0.23
     themselves
    0.23
     himself
    0.23
     yourself
    0.21
     oneself
    0.21
     siÄĻ
    0.19
     myself
    0.19
     ourselves
    0.18
    Act Density 0.243%

    No Known Activations