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

    Neuronpedia

    INDEX
    Explanations

    references to the act of learning about different events, incidents, or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of learning or gaining information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     attRot
    -0.64
    "))
    -0.61
    ]);
    -0.60
    atever
    -0.59
    ]),
    -0.59
    otin
    -0.57
    %).
    -0.56
    %.
    -0.56
    ])
    -0.56
     blot
    -0.53
    POSITIVE LOGITS
     shortly
    1.21
     AFTER
    1.00
     after
    1.00
     sometime
    0.97
     via
    0.88
     late
    0.87
     thanks
    0.86
     when
    0.86
     early
    0.85
     earlier
    0.85
    Act Density 0.646%

    No Known Activations