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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes or transitions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to change and response in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     */
    -0.65
    ®,
    -0.63
     ..."
    -0.61
    joice
    -0.61
     [&
    -0.60
     EVERY
    -0.60
     someday
    -0.60
    hovah
    -0.60
    ↵Âł
    -0.59
    ++;
    -0.59
    POSITIVE LOGITS
     resignation
    0.77
     criticism
    0.75
     deliberations
    0.72
     reaction
    0.72
     briefings
    0.71
     criticisms
    0.70
     reactions
    0.70
     controversies
    0.69
     accusations
    0.68
     consultations
    0.68
    Act Density 1.434%

    No Known Activations