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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries about information and processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.07
     Efq
    -1.02
    NUMX
    -0.96
     Monfieur
    -0.96
    saraba
    -0.94
    Personensuche
    -0.91
     Theſe
    -0.90
     ſeveral
    -0.88
     $_"
    -0.86
    indd
    -0.84
    POSITIVE LOGITS
    ?
    0.70
    ?.
    0.59
     ?
    0.51
    ue
    0.48
     Answer
    0.48
    ?,
    0.48
    yes
    0.46
     YES
    0.45
     yes
    0.44
    Answer
    0.44
    Act Density 0.223%

    No Known Activations