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

    Neuronpedia

    INDEX
    Explanations

    assertions or claims related to observations and discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     a
    -0.52
     
    -0.51
     "
    -0.51
    <bos>
    -0.51
     Bar
    -0.49
     __
    -0.49
    iol
    -0.48
    .*")]
    -0.47
     **
    -0.47
    jsonwebtoken
    -0.47
    POSITIVE LOGITS
     myſelf
    0.85
     flamengo
    0.76
     Monfieur
    0.75
     Efq
    0.74
     itſelf
    0.73
     initComponents
    0.72
     auffi
    0.70
     uſed
    0.67
     Theſe
    0.66
     himſelf
    0.66
    Act Density 0.279%

    No Known Activations