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

    Neuronpedia

    INDEX
    Explanations

    instances of looking or staring interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     underst
    -0.16
    овÑĸд
    -0.15
    ensed
    -0.15
    uire
    -0.15
    readcr
    -0.15
    ummings
    -0.14
     hed
    -0.14
    alous
    -0.14
    iman
    -0.14
    endon
    -0.14
    POSITIVE LOGITS
    tv
    0.15
    osten
    0.15
     circuit
    0.14
     faces
    0.14
     ÑģÑĤанÑĥ
    0.13
    reflection
    0.13
     Circuit
    0.13
     Beans
    0.13
     Spencer
    0.13
    rote
    0.13
    Act Density 0.102%

    No Known Activations