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

    Neuronpedia

    INDEX
    Explanations

    the prefix "un-" indicating negation or the absence of a quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.30
     ſche
    -1.22
     MainAxisSize
    -1.20
     myſelf
    -1.19
     itſelf
    -1.11
     ainfi
    -1.11
     houſe
    -1.09
     becauſe
    -1.05
     ―――――
    -1.04
     Majefty
    -1.03
    POSITIVE LOGITS
     un
    1.58
     Un
    1.53
    Un
    1.27
     UN
    1.18
    un
    1.13
    UN
    0.97
     pre
    0.94
     Pre
    0.94
    有不
    0.87
     G
    0.83
    Act Density 0.055%

    No Known Activations