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

    Neuronpedia

    INDEX
    Explanations

    references to web or API structures and specifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.67
     "
    -0.65
     ST
    -0.62
     M
    -0.60
     '
    -0.56
    -
    -0.56
     (
    -0.56
     or
    -0.53
     St
    -0.52
     s
    -0.51
    POSITIVE LOGITS
     itſelf
    1.16
     pleaſure
    1.15
    ſelves
    1.01
     ſtate
    0.99
     незавершена
    0.99
     auffi
    0.96
     myſelf
    0.95
     nakalista
    0.95
     purpoſe
    0.92
     houſe
    0.92
    Act Density 0.001%

    No Known Activations