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

    Neuronpedia

    INDEX
    Explanations

    prefixes related to the concept of "not" or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uze
    -0.18
     Entr
    -0.15
    oser
    -0.15
    dex
    -0.15
    odo
    -0.14
    effective
    -0.14
    аниÑĨ
    -0.14
     Oper
    -0.14
    zyst
    -0.13
     declarations
    -0.13
    POSITIVE LOGITS
    erring
    0.29
    ending
    0.26
    flag
    0.23
    shake
    0.23
    rel
    0.23
    ash
    0.22
    match
    0.21
    yield
    0.21
    brid
    0.21
    ifying
    0.21
    Act Density 0.026%

    No Known Activations