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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conspiracies and plots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TERN
    -0.17
    avia
    -0.16
    jÅ¡ÃŃ
    -0.15
    ELS
    -0.14
    aser
    -0.14
    ikel
    -0.14
     ÑģкладÑĥ
    -0.14
    esso
    -0.14
    StreamWriter
    -0.14
    torrent
    -0.14
    POSITIVE LOGITS
     behind
    0.17
    kowski
    0.17
    à¤ļन
    0.14
     Farr
    0.14
    eam
    0.14
    pus
    0.14
     dens
    0.14
    /request
    0.14
     against
    0.13
     Entrance
    0.13
    Act Density 0.021%

    No Known Activations