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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate feelings and personal significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ü
    -0.17
    ysis
    -0.16
    caa
    -0.16
     slip
    -0.15
     Cabin
    -0.15
    htar
    -0.13
    bare
    -0.13
     Sche
    -0.13
    este
    -0.13
    amiliar
    -0.13
    POSITIVE LOGITS
     me
    0.30
     us
    0.21
    æĪij
    0.18
     tôi
    0.17
     saya
    0.16
    íĨµ
    0.16
    INGTON
    0.16
    atham
    0.15
     VID
    0.15
    ovel
    0.15
    Act Density 0.116%

    No Known Activations