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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "jump" and its variations, indicating a focus on jumping actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.71
     дописавши
    -0.65
    الحياه
    -0.62
     NSCoder
    -0.60
     étrangères
    -0.57
    oneofs
    -0.57
    Datuak
    -0.56
    GeneratedCode
    -0.54
    HomeAsUpEnabled
    -0.54
    ModelState
    -0.53
    POSITIVE LOGITS
     jump
    3.89
     Jump
    3.63
    jump
    3.51
    Jump
    3.39
     jumps
    3.38
     JUMP
    3.33
     jumping
    3.23
     jumped
    3.21
     Jumping
    2.90
    jumping
    2.87
    Act Density 0.035%

    No Known Activations