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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and administrative divisions, specifically counties and cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ury
    -0.18
     Nob
    -0.15
    owan
    -0.15
    noop
    -0.15
    pek
    -0.14
     Rut
    -0.14
    cano
    -0.14
    ias
    -0.14
    efs
    -0.14
    ildo
    -0.14
    POSITIVE LOGITS
     Aires
    0.18
    ashtra
    0.15
    createView
    0.14
    _HIDE
    0.14
    ENC
    0.14
     Merlin
    0.13
    ccoli
    0.13
    EMON
    0.13
    lies
    0.13
    acher
    0.13
    Act Density 0.042%

    No Known Activations