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

    Neuronpedia

    INDEX
    Explanations

    words related to personal behavior and habits

    oai_token-act-pair · gpt-3.5-turbo

    expressions of psychological states and behaviors related to distraction and obsession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resumed
    -0.79
     restored
    -0.66
     totaled
    -0.66
    asus
    -0.66
    ONDON
    -0.64
     recovered
    -0.64
    çīĪ
    -0.64
    ongyang
    -0.62
     freed
    -0.61
     Liberation
    -0.60
    POSITIVE LOGITS
     whenever
    1.20
     sometimes
    1.10
     unnecessarily
    1.10
     when
    1.05
     unconsciously
    0.98
     inappropriately
    0.96
    sometimes
    0.96
     depending
    0.95
     blindly
    0.95
     awkwardly
    0.94
    Act Density 0.418%

    No Known Activations