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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or government terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing disappointment or frustration about unmet expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pyramid
    -0.60
     topic
    -0.58
     moot
    -0.58
     prone
    -0.58
     subject
    -0.57
     subordinate
    -0.57
     question
    -0.56
    ilant
    -0.56
    MO
    -0.55
     complicit
    -0.54
    POSITIVE LOGITS
    been
    1.31
     been
    1.03
     Been
    0.93
    gotten
    0.82
     gotten
    0.80
    yet
    0.77
    ãĤ¦ãĤ¹
    0.72
     undergone
    0.71
    since
    0.69
     mastered
    0.68
    Act Density 0.073%

    No Known Activations