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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and taking steps

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to collective actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilty
    -0.70
    Relations
    -0.68
     recognition
    -0.68
     sensing
    -0.68
     resemblance
    -0.66
    Reply
    -0.64
     enjoyment
    -0.64
    comings
    -0.63
     conviction
    -0.63
     witnessing
    -0.62
    POSITIVE LOGITS
     resorted
    1.46
     opted
    1.27
     devised
    1.26
     decided
    1.19
     instituted
    1.09
     undertook
    1.06
     chose
    1.04
     teamed
    1.01
     enlisted
    1.01
     embarked
    0.98
    Act Density 0.308%

    No Known Activations