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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transitions or changes

    oai_token-act-pair · gpt-3.5-turbo

    references to transitions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Copyright
    -0.64
    ãĥĩãĤ£
    -0.63
    conn
    -0.63
     Gladiator
    -0.59
    CVE
    -0.59
     Smile
    -0.59
    ñ
    -0.59
     Logged
    -0.59
     WARN
    -0.58
    stri
    -0.58
    POSITIVE LOGITS
    ogue
    0.87
     period
    0.85
     transition
    0.83
     between
    0.83
    aroo
    0.80
     seamlessly
    0.78
     into
    0.76
     periods
    0.76
    ivating
    0.75
     Transition
    0.75
    Act Density 0.039%

    No Known Activations