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

    Neuronpedia

    INDEX
    Explanations

    evidence and details relevant to specific events or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -2.03
     itſelf
    -1.96
     purpoſe
    -1.89
     Jefus
    -1.88
     pleaſure
    -1.86
     Efq
    -1.81
     Monfieur
    -1.80
     ſeveral
    -1.71
     themſelves
    -1.71
     ſever
    -1.69
    POSITIVE LOGITS
     et
    0.74
     ad
    0.63
     est
    0.53
     pro
    0.53
     ab
    0.52
    que
    0.51
     qu
    0.51
     ex
    0.50
     non
    0.49
     f
    0.47
    Act Density 0.245%

    No Known Activations