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

    Neuronpedia

    INDEX
    Explanations

    mentions of "press" or "press releases"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sá»ķ
    -0.17
    ลาà¸Ķ
    -0.16
    qing
    -0.15
    asses
    -0.15
    ĵ¨
    -0.15
    atables
    -0.15
    chy
    -0.14
    jal
    -0.14
    è·¡
    -0.14
    LETE
    -0.14
    POSITIVE LOGITS
    uring
    0.30
    ures
    0.29
    ur
    0.29
    ured
    0.24
    sure
    0.24
    room
    0.23
    umably
    0.22
    sing
    0.21
     conference
    0.21
    er
    0.21
    Act Density 0.018%

    No Known Activations