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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating locations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imon
    -0.16
     yıllık
    -0.15
     contrad
    -0.15
     surfaces
    -0.14
     Wake
    -0.14
    rost
    -0.14
    nehmen
    -0.14
    PEND
    -0.14
    perty
    -0.14
     expiration
    -0.14
    POSITIVE LOGITS
     middle
    0.23
     shower
    0.20
     distance
    0.17
     chair
    0.17
    middle
    0.17
    -middle
    0.17
     audience
    0.17
     bushes
    0.17
     crowd
    0.16
     office
    0.16
    Act Density 0.169%

    No Known Activations