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

    Neuronpedia

    INDEX
    Explanations

    superlative adjectives and comparative terms related to size, depth, speed, and brightness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     T
    -0.88
     k
    -0.83
     Z
    -0.82
     Mat
    -0.82
     K
    -0.79
     p
    -0.78
     J
    -0.78
     j
    -0.77
     l
    -0.77
    T
    -0.77
    POSITIVE LOGITS
     myſelf
    1.82
     itſelf
    1.68
     leſs
    1.59
    ſelves
    1.55
     himſelf
    1.52
     Anſ
    1.50
    ſelf
    1.48
     pleaſure
    1.44
     ་་
    1.44
     Majefty
    1.43
    Act Density 0.163%

    No Known Activations