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

    Neuronpedia

    INDEX
    Explanations

    the start of new sections or significant breaks in the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.08
     itſelf
    -1.04
     Jefus
    -0.95
     Majefty
    -0.93
     Efq
    -0.92
     poffible
    -0.89
     themſelves
    -0.85
     himſelf
    -0.84
     iſt
    -0.83
     fubject
    -0.83
    POSITIVE LOGITS
     
    0.70
     "
    0.63
    \
    0.61
    ${
    0.58
    paraiso
    0.58
    <bos>
    0.57
    "+
    0.52
     ...
    0.52
    migrationBuilder
    0.51
    enumi
    0.51
    Act Density 0.087%

    No Known Activations