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

    Neuronpedia

    INDEX
    Explanations

    terms related to authority, power dynamics, and negotiation outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ribbon
    -0.19
    anggan
    -0.16
    곤
    -0.16
    asio
    -0.15
    _Tick
    -0.15
    ãĥ«ãĥī
    -0.15
    igte
    -0.15
    adoo
    -0.14
     عبار
    -0.14
    jac
    -0.14
    POSITIVE LOGITS
     Lore
    0.19
    óm
    0.15
     Glo
    0.14
    261
    0.14
    essler
    0.14
    аков
    0.14
    thood
    0.14
    _COMPILE
    0.14
     lore
    0.14
     Tam
    0.14
    Act Density 0.038%

    No Known Activations