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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of inability or reluctance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adb
    -0.16
    ickle
    -0.16
    uras
    -0.15
    aram
    -0.15
    tc
    -0.15
    -svg
    -0.15
    æ·»
    -0.15
     Ple
    -0.14
    ost
    -0.14
    upp
    -0.14
    POSITIVE LOGITS
     resist
    0.32
     Resist
    0.26
     resisted
    0.24
     resisting
    0.23
     stomach
    0.21
     resistor
    0.20
    Resistance
    0.20
     ÙħÙĤاÙĪ
    0.19
    suppress
    0.19
     resistance
    0.19
    Act Density 0.103%

    No Known Activations