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

    Neuronpedia

    INDEX
    Explanations

    terms of endearment or greetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsk
    -0.16
    edo
    -0.16
    aroo
    -0.16
    gia
    -0.15
    oodle
    -0.15
    gers
    -0.15
    entric
    -0.15
    innacle
    -0.15
    à¸ķะว
    -0.14
    ous
    -0.14
    POSITIVE LOGITS
    íŀĪ
    0.20
     departed
    0.18
    acket
    0.16
    born
    0.16
    ì½
    0.15
    lies
    0.15
    ths
    0.15
    ings
    0.15
     ÙĪاØŃ
    0.15
    liest
    0.14
    Act Density 0.010%

    No Known Activations