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

    Neuronpedia

    INDEX
    Explanations

    references to various types of houses or buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fare
    -0.17
    icot
    -0.16
    OOSE
    -0.15
    pon
    -0.14
    avs
    -0.13
    rias
    -0.13
    bane
    -0.13
    lal
    -0.13
    hang
    -0.13
    utt
    -0.13
    POSITIVE LOGITS
    ynom
    0.17
    swire
    0.16
    apis
    0.15
    ÑģÑĤÑĢи
    0.15
    doors
    0.14
    êu
    0.14
    oken
    0.14
    OKEN
    0.14
    ento
    0.14
    ियत
    0.14
    Act Density 0.015%

    No Known Activations