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

    Neuronpedia

    INDEX
    Explanations

    words related to political ideologies and figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Embal
    -0.63
    setTimestamp
    -0.62
    ^{*}=
    -0.61
    <bos>
    -0.58
     vPvB
    -0.58
     nadzieję
    -0.57
    ModelBuilder
    -0.57
    \{\\
    -0.56
     gwaran
    -0.56
    kedés
    -0.56
    POSITIVE LOGITS
     fup
    1.53
     sii
    1.53
     wien
    1.48
     mef
    1.47
     Fasc
    1.45
     curi
    1.44
     fta
    1.43
     nece
    1.43
     „,
    1.42
     stockholm
    1.42
    Act Density 0.188%

    No Known Activations