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

    Neuronpedia

    INDEX
    Explanations

    references to ex-partners or ex-spouses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Excell
    -0.19
    prites
    -0.15
    sons
    -0.15
    post
    -0.14
     extras
    -0.14
    flex
    -0.14
    æ´¥
    -0.14
     excess
    -0.13
    panies
    -0.13
    beans
    -0.13
    POSITIVE LOGITS
    es
    0.25
    asper
    0.22
    uber
    0.20
    iled
    0.20
    -boy
    0.20
    orc
    0.19
    orbit
    0.18
    -girl
    0.18
     ex
    0.18
    /current
    0.17
    Act Density 0.006%

    No Known Activations