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

    Neuronpedia

    INDEX
    Explanations

    concepts related to historical perspectives and societal critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assin
    -0.17
    룴
    -0.14
    CHASE
    -0.14
     onDataChange
    -0.13
    URY
    -0.13
    .scalablytyped
    -0.13
    ÏĢοÏį
    -0.13
    .='
    -0.12
    _impl
    -0.12
     cazzo
    -0.12
    POSITIVE LOGITS
     differently
    0.37
     negatively
    0.27
     as
    0.26
     like
    0.24
     unfavor
    0.22
     positively
    0.21
     neutr
    0.20
     simpl
    0.20
     skept
    0.20
     synonym
    0.20
    Act Density 0.158%

    No Known Activations