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

    Neuronpedia

    INDEX
    Explanations

    repetitive patterns and sequences in procedural or mechanical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fro
    -0.14
     Jones
    -0.14
    scal
    -0.14
     sleeper
    -0.14
     Manning
    -0.14
    amaz
    -0.13
     movable
    -0.13
     Reconstruction
    -0.13
    emoc
    -0.13
    azzi
    -0.13
    POSITIVE LOGITS
     cycles
    0.31
     cycle
    0.28
     session
    0.24
     rounds
    0.24
    cycles
    0.23
    -cycle
    0.22
     lần
    0.22
     次
    0.22
     sessions
    0.22
     round
    0.21
    Act Density 0.261%

    No Known Activations