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

    Neuronpedia

    INDEX
    Explanations

    references to scientific or technical concepts, particularly those related to studies or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aber
    -0.47
     autorytatywna
    -0.44
    chrift
    -0.43
    CppMethod
    -0.43
    chenk
    -0.41
    ulio
    -0.41
    moor
    -0.40
     Moor
    -0.40
    Autoritní
    -0.40
    wnątrz
    -0.40
    POSITIVE LOGITS
     anymore
    0.72
    InputBorder
    0.65
    ThroughAttribute
    0.65
     whoſe
    0.62
     houſe
    0.61
     ſtate
    0.57
    windowFixed
    0.57
    qrstuvwxyz
    0.57
     ſte
    0.57
     becauſe
    0.55
    Act Density 1.397%

    No Known Activations