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

    Neuronpedia

    INDEX
    Explanations

    verbs related to change, development, or progression

    oai_token-act-pair · gpt-3.5-turbo

    words related to change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocations
    -0.68
    oops
    -0.67
    cest
    -0.66
    ãĤ¦ãĤ¹
    -0.66
    è¦ļéĨĴ
    -0.63
    DCS
    -0.62
    fill
    -0.62
    bash
    -0.62
    ãĥīãĥ©
    -0.61
    ourt
    -0.61
    POSITIVE LOGITS
     into
    1.32
     rapidly
    1.20
     exponentially
    1.09
     smoothly
    1.05
     considerably
    1.02
     nicely
    0.98
     seamlessly
    0.97
     INTO
    0.96
     explos
    0.95
     peacefully
    0.95
    Act Density 0.193%

    No Known Activations