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

    Neuronpedia

    INDEX
    Explanations

    sections that discuss proposals, studies, or structured research outputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     /
    -0.81
     /\
    -0.78
     *
    -0.72
     .
    -0.72
     (
    -0.71
     \
    -0.69
     =
    -0.64
     S
    -0.64
     (\
    -0.64
     ((
    -0.64
    POSITIVE LOGITS
     Efq
    1.15
     Majefty
    1.14
     myſelf
    1.13
     itſelf
    1.12
     Diſ
    1.04
     Normdatei
    1.03
     Houſe
    1.02
    ſelf
    1.01
     themſelves
    1.01
     purpoſe
    1.00
    Act Density 0.124%

    No Known Activations