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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate an aspect of conflict or duality in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hardy
    -0.15
    iere
    -0.15
    547
    -0.15
    ãĥ³ãĤº
    -0.15
    rypton
    -0.14
     Trident
    -0.14
    rant
    -0.14
    enders
    -0.14
    dos
    -0.14
     Exercise
    -0.13
    POSITIVE LOGITS
    ais
    0.17
    ần
    0.16
    tility
    0.15
    Pont
    0.15
    alink
    0.14
    ÙĦاÙĦ
    0.14
    utt
    0.14
     Mobility
    0.14
    oen
    0.14
     end
    0.13
    Act Density 0.000%

    No Known Activations