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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "make" and its variations, indicating a focus on creation or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actics
    -0.15
    \<^
    -0.15
    nda
    -0.15
    ̣
    -0.14
    itis
    -0.14
    warn
    -0.14
    ±Ð¾ÑĤ
    -0.14
    çŃĶæ¡Ī
    -0.14
    awan
    -0.14
    StdString
    -0.13
    POSITIVE LOGITS
     mistake
    0.29
     mistakes
    0.28
     noises
    0.26
     contribution
    0.26
     noise
    0.26
     choices
    0.23
    mist
    0.23
     distinction
    0.23
     connection
    0.23
     strides
    0.22
    Act Density 0.145%

    No Known Activations