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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical locations or positions in relation to other objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chi
    -0.15
    оÑĢоÑĪ
    -0.15
    antis
    -0.15
    меÑĩ
    -0.15
    TickCount
    -0.15
    NSSet
    -0.14
    isté
    -0.14
     ë°
    -0.14
    elo
    -0.14
    æ¡IJ
    -0.13
    POSITIVE LOGITS
     scenes
    0.27
     Scenes
    0.24
    -scenes
    0.23
    scenes
    0.22
     Behind
    0.20
     behind
    0.19
    Behind
    0.17
     curtain
    0.17
     Curtain
    0.17
    vents
    0.16
    Act Density 0.050%

    No Known Activations