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

    Neuronpedia

    INDEX
    Explanations

    references to political ideologies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UMAN
    -0.16
    omet
    -0.15
    /preferences
    -0.15
    ë¥´ê³ł
    -0.14
    ISC
    -0.13
    άνÏī
    -0.13
    hape
    -0.13
    ulumi
    -0.13
    bsolute
    -0.13
    _CALLBACK
    -0.13
    POSITIVE LOGITS
     anti
    0.25
     comb
    0.22
     pro
    0.21
     defensive
    0.21
     inflammatory
    0.20
     confront
    0.20
     particip
    0.20
    flammatory
    0.20
     protective
    0.19
     inclusive
    0.19
    Act Density 0.332%

    No Known Activations