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

    Neuronpedia

    INDEX
    Explanations

    verbs in the infinitive form preceded by "to"

    oai_token-act-pair · gpt-3.5-turbo

    instances of decision-making or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.79
    Lear
    -0.79
    ĺħ
    -0.74
     comprehension
    -0.68
    anooga
    -0.68
    felt
    -0.65
    ivia
    -0.64
    ģĸ
    -0.62
    oken
    -0.62
    umerable
    -0.62
    POSITIVE LOGITS
     pursue
    1.39
     postpone
    1.32
     ignore
    1.26
     omit
    1.26
     terminate
    1.22
     proceed
    1.19
     abandon
    1.18
     exclude
    1.17
     prioritize
    1.16
     dedicate
    1.15
    Act Density 0.170%

    No Known Activations