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

    Neuronpedia

    INDEX
    Explanations

    occurrences of tense shifts or actions related to decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inger
    -0.17
    ingers
    -0.14
    айд
    -0.14
     wherever
    -0.14
    Recovered
    -0.14
    heim
    -0.14
    UCT
    -0.14
    inx
    -0.13
    uhan
    -0.13
    idential
    -0.13
    POSITIVE LOGITS
     fallback
    0.18
     frustration
    0.16
    orra
    0.16
     resort
    0.16
    æĸ¹æ¡Ī
    0.16
     despair
    0.15
     frustrated
    0.15
    ibar
    0.15
    失败
    0.15
    ery
    0.15
    Act Density 0.398%

    No Known Activations