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

    Neuronpedia

    INDEX
    Explanations

    affirmative statements about experiences and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anel
    -0.17
    alem
    -0.17
    resse
    -0.16
    ä¿¡çĶ¨
    -0.15
    xcd
    -0.15
    antz
    -0.15
    amerate
    -0.14
    assic
    -0.14
    annel
    -0.14
    loe
    -0.14
    POSITIVE LOGITS
    üçük
    0.16
    otos
    0.15
    æ¨ĵ
    0.15
    ulled
    0.14
     real
    0.14
    است
    0.14
    372
    0.14
    åºŃ
    0.13
    ĵ°
    0.13
    楼
    0.13
    Act Density 0.005%

    No Known Activations