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

    Neuronpedia

    INDEX
    Explanations

    expressions of refusal and determination in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lag
    -0.18
    vÃŃce
    -0.16
    iso
    -0.15
    defgroup
    -0.14
    ico
    -0.14
    yn
    -0.13
    eless
    -0.13
     Tep
    -0.13
     Elevated
    -0.13
     Labels
    -0.13
    POSITIVE LOGITS
     firm
    0.25
     fixed
    0.22
    fixed
    0.20
    åĽº
    0.19
     flex
    0.19
     Firm
    0.19
     immutable
    0.18
     flexibility
    0.17
     Flex
    0.17
    firm
    0.17
    Act Density 0.244%

    No Known Activations