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

    Neuronpedia

    INDEX
    Explanations

    expressions of skepticism or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Terms
    -0.14
    indsight
    -0.14
     ÑĥÑģÑĤанов
    -0.14
    ẹn
    -0.14
    pong
    -0.14
    oir
    -0.13
    èĦ
    -0.13
    aeda
    -0.13
    unch
    -0.13
    ëĪĦ
    -0.13
    POSITIVE LOGITS
     directly
    0.40
     somehow
    0.32
     direct
    0.28
    direct
    0.28
     DIRECT
    0.28
     напÑĢÑıм
    0.27
     specifically
    0.26
     indirectly
    0.26
     possible
    0.23
     diret
    0.23
    Act Density 0.014%

    No Known Activations