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

    Neuronpedia

    INDEX
    Explanations

    comparisons or similes in the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -1.29
     purpoſe
    -1.25
     Efq
    -1.17
     ſever
    -1.16
    ſelves
    -1.16
     perſon
    -1.15
     myſelf
    -1.14
     raiſ
    -1.14
     itſelf
    -1.14
     houſe
    -1.13
    POSITIVE LOGITS
    '
    0.67
    !
    0.67
      
    0.66
    .
    0.66
     
    0.63
    ’
    0.62
    /
    0.62
     I
    0.60
    ,
    0.58
     a
    0.58
    Act Density 0.067%

    No Known Activations