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

    Neuronpedia

    INDEX
    Explanations

    references to political parties and ideologies, especially those associated with extremism or historical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eskort
    -0.16
    olley
    -0.15
     kå
    -0.15
     Bias
    -0.14
    etal
    -0.14
    CHA
    -0.14
    rotch
    -0.14
    celik
    -0.14
    assis
    -0.14
    ester
    -0.14
    POSITIVE LOGITS
     party
    0.26
     split
    0.24
     splits
    0.23
     spl
    0.23
     formations
    0.22
     Party
    0.20
     splitter
    0.20
     ide
    0.20
     contest
    0.20
     membership
    0.20
    Act Density 0.074%

    No Known Activations