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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.17
    üst
    -0.16
    ecess
    -0.15
    обÑĢаз
    -0.15
    aina
    -0.15
     Loren
    -0.15
    tet
    -0.15
    oral
    -0.15
     rej
    -0.15
    ambi
    -0.14
    POSITIVE LOGITS
     ward
    0.19
    /down
    0.18
    wards
    0.18
     wards
    0.17
    yun
    0.17
    WARDS
    0.16
    ozilla
    0.16
    rightness
    0.16
    è¾¾
    0.16
    otre
    0.15
    Act Density 0.023%

    No Known Activations