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

    Neuronpedia

    INDEX
    Explanations

    references to work and organizational structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.15
    à¹ĥà¸Ī
    -0.14
    plies
    -0.13
    ãng
    -0.13
    'gc
    -0.13
    راد
    -0.13
    yses
    -0.12
    ży
    -0.12
    tribute
    -0.12
    ithe
    -0.12
    POSITIVE LOGITS
     etc
    0.30
     stuff
    0.26
    etc
    0.26
     they
    0.26
     it
    0.24
     there
    0.24
     we
    0.22
     if
    0.21
     this
    0.21
    this
    0.21
    Act Density 0.611%

    No Known Activations