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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the prefix "un," indicating a focus on negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.26
     MainAxisSize
    -1.14
     myſelf
    -1.12
     ſche
    -1.10
     ainfi
    -1.10
     becauſe
    -1.04
     ་་
    -1.03
     ―――――
    -1.02
     Majefty
    -1.01
     Beſ
    -1.00
    POSITIVE LOGITS
     Un
    1.61
     un
    1.52
    Un
    1.39
     UN
    1.32
    un
    1.24
    UN
    1.14
    有不
    0.91
     Al
    0.86
     Uns
    0.84
     Uni
    0.83
    Act Density 0.085%

    No Known Activations