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

    Neuronpedia

    INDEX
    Explanations

    keywords related to various fields including education, delivery services, and technological research

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     "
    -0.48
    調
    -0.48
     so
    -0.47
     an
    -0.47
     id
    -0.47
    ?
    -0.47
     out
    -0.46
     on
    -0.46
     u
    -0.44
     i
    -0.43
    POSITIVE LOGITS
     myſelf
    0.89
     pleaſure
    0.87
     reaſon
    0.81
     raiſ
    0.81
    +#+#
    0.81
     ſever
    0.79
     Anſ
    0.78
     purpoſe
    0.77
     ſeveral
    0.76
     themſelves
    0.75
    Act Density 0.135%

    No Known Activations