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

    Neuronpedia

    INDEX
    Explanations

    expressions of authenticity and sincerity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sson
    -0.17
     mere
    -0.16
     赤
    -0.14
    _INF
    -0.14
    ä»ĺ
    -0.14
    ersion
    -0.14
     congress
    -0.14
    sil
    -0.14
    al
    -0.14
     INFO
    -0.14
    POSITIVE LOGITS
    uggle
    0.16
    chaft
    0.16
    arrants
    0.15
    isten
    0.15
    uby
    0.15
    uger
    0.14
    omitempty
    0.14
    /false
    0.14
    vero
    0.14
     Ocak
    0.14
    Act Density 0.012%

    No Known Activations