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

    Neuronpedia

    INDEX
    Explanations

    mentions of hotel names and associated amenities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zza
    -0.17
    Vac
    -0.15
    vac
    -0.15
    ycastle
    -0.15
    Remote
    -0.15
     RemoteException
    -0.15
     OTHERWISE
    -0.15
     gra
    -0.14
    _fid
    -0.14
     Ñģом
    -0.14
    POSITIVE LOGITS
    siz
    0.16
    ords
    0.15
    idian
    0.15
    indi
    0.14
     chains
    0.14
    oux
    0.14
     ---------------------------------------------------------------------------↵
    0.13
    errick
    0.13
    otel
    0.13
    indle
    0.13
    Act Density 0.013%

    No Known Activations