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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to experiences of confusion or disorientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MESS
    -0.17
    istar
    -0.17
    genesis
    -0.17
    oldt
    -0.16
    DAT
    -0.16
    cho
    -0.15
     DAT
    -0.15
    lom
    -0.15
    rys
    -0.14
    ýn
    -0.14
    POSITIVE LOGITS
    taire
    0.18
    ohana
    0.15
    ãģĹãģĭ
    0.15
    wg
    0.14
    thur
    0.14
    поÑĢ
    0.13
    098
    0.13
    CLU
    0.13
    aul
    0.13
    .observe
    0.13
    Act Density 0.000%

    No Known Activations