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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing guidance or instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "how" processes and actions are carried out

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     )]
    -0.66
     Grail
    -0.64
    isher
    -0.61
     Thief
    -0.60
     Mercenary
    -0.60
    ãĤ«
    -0.60
     Goth
    -0.57
     Gast
    -0.57
     Fairy
    -0.56
     Kou
    -0.56
    POSITIVE LOGITS
    soever
    1.10
    beit
    0.89
    ever
    0.85
    HCR
    0.83
    itzer
    0.78
    ricanes
    0.78
     nomine
    0.78
     exactly
    0.72
    paio
    0.71
    ls
    0.70
    Act Density 0.075%

    No Known Activations