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

    Neuronpedia

    INDEX
    Explanations

    references to specific lanes or pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    URLEncoder
    -0.59
     abogado
    -0.57
    wor
    -0.55
    ✉
    -0.54
    Meta
    -0.52
    Unset
    -0.51
    var
    -0.51
    meta
    -0.49
     Weib
    -0.49
    const
    -0.49
    POSITIVE LOGITS
     ProtoMessage
    0.91
    Exercises
    0.90
     Exercises
    0.86
    Exercise
    0.86
     capsules
    0.85
    exercises
    0.85
     exercises
    0.82
     Exercise
    0.81
    StructEnd
    0.81
    exercise
    0.78
    Act Density 0.246%

    No Known Activations