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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that express numerical thresholds or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymi
    -0.17
     Kral
    -0.15
    .timestamps
    -0.15
     Existing
    -0.15
     Castillo
    -0.15
    urovision
    -0.14
    kud
    -0.14
     Increment
    -0.14
     náro
    -0.13
    Pin
    -0.13
    POSITIVE LOGITS
    enever
    0.14
    PickerController
    0.14
    erm
    0.14
     than
    0.14
    ollect
    0.14
    hound
    0.14
    ynam
    0.13
    .dom
    0.13
    омеÑĢ
    0.13
    907
    0.13
    Act Density 0.344%

    No Known Activations