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

    Neuronpedia

    INDEX
    Explanations

    references to containers, particularly 'buckets' and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adera
    -0.17
    ãĥĨãĥ«
    -0.14
    uddle
    -0.14
    çłģ
    -0.14
    itung
    -0.14
    leck
    -0.14
    ylene
    -0.14
    outu
    -0.14
    StackSize
    -0.14
     Gad
    -0.13
    POSITIVE LOGITS
    eras
    0.15
    obbies
    0.15
     Thor
    0.15
     eens
    0.14
    pte
    0.14
    abal
    0.14
    acha
    0.14
     Struct
    0.14
    umbn
    0.13
    òi
    0.13
    Act Density 0.006%

    No Known Activations