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

    Neuronpedia

    INDEX
    Explanations

    terms associated with influence or impact on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.77
     myſelf
    -1.75
     doubtnut
    -1.74
     purpoſe
    -1.71
    ſelf
    -1.71
     Efq
    -1.71
     pleaſure
    -1.70
     itſelf
    -1.66
    ſelves
    -1.64
     poffible
    -1.57
    POSITIVE LOGITS
     affecting
    1.07
     
    1.00
    ↵
    0.90
     (
    0.87
     I
    0.86
     "
    0.85
     The
    0.83
     -
    0.82
     [
    0.81
    ↵↵
    0.80
    Act Density 0.423%

    No Known Activations