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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate limitations or boundaries in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rna
    -0.16
    kiem
    -0.15
    wick
    -0.15
    dana
    -0.15
    ias
    -0.15
    angi
    -0.14
    ulton
    -0.14
    ÑģÑĤа
    -0.14
    姿
    -0.13
    icher
    -0.13
    POSITIVE LOGITS
     extent
    0.69
    extent
    0.53
     extents
    0.47
     degree
    0.46
     detriment
    0.42
     tune
    0.41
     extend
    0.39
    .extent
    0.36
    degree
    0.33
     point
    0.33
    Act Density 0.105%

    No Known Activations