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

    Neuronpedia

    INDEX
    Explanations

    significant components related to actions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uner
    -0.18
    ruta
    -0.16
    ãĤīãģı
    -0.15
    ilenames
    -0.15
    gnore
    -0.14
    rots
    -0.14
    ainer
    -0.14
    inks
    -0.14
    mav
    -0.14
    溶
    -0.13
    POSITIVE LOGITS
    orca
    0.17
    antis
    0.15
    orrow
    0.15
    yar
    0.14
    iras
    0.14
    _BT
    0.14
    rov
    0.14
    irates
    0.13
    oshi
    0.13
    ,LOCATION
    0.13
    Act Density 0.013%

    No Known Activations