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

    Neuronpedia

    INDEX
    Explanations

    references to infidelity and romantic relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    noc
    -0.16
    psc
    -0.16
     Bols
    -0.15
    Unused
    -0.15
    Extern
    -0.15
    PERT
    -0.15
    ãĥ³ãĥĦ
    -0.15
    _pitch
    -0.15
    ailable
    -0.14
    εβ
    -0.14
    POSITIVE LOGITS
     dall
    0.18
     gall
    0.17
    683
    0.15
     tup
    0.15
     serial
    0.15
     extr
    0.15
     USDA
    0.14
     relationships
    0.14
     lur
    0.14
     conc
    0.14
    Act Density 0.146%

    No Known Activations