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

    Neuronpedia

    INDEX
    Explanations

    the prefix "un-" in words, indicating negation or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prefixes: un-, pro-, re-, dis-

    np_acts-logits-general · gemini-2.0-flash

    un- prefixes, re-, pro-, dis-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Theſe
    -1.29
     ་་
    -1.28
     ainfi
    -1.18
    BibitemShut
    -1.16
     itſelf
    -1.15
     ―――――
    -1.07
     myſelf
    -1.04
     Beſ
    -1.01
     Monfieur
    -1.00
    }%
    -0.99
    POSITIVE LOGITS
    O
    1.03
    G
    0.99
    S
    0.99
    P
    0.99
    U
    0.97
    R
    0.97
    N
    0.96
    E
    0.95
    Re
    0.95
    W
    0.91
    Act Density 0.222%

    No Known Activations