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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions or taking action

    oai_token-act-pair · gpt-3.5-turbo

    references to decision-making processes and collective actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorable
    -0.72
    Relations
    -0.69
    /+
    -0.67
     Notice
    -0.63
     Estimated
    -0.63
    iability
    -0.61
    ilty
    -0.61
    Notice
    -0.61
     enjoyment
    -0.60
    miss
    -0.59
    POSITIVE LOGITS
     devised
    0.95
     resorted
    0.86
     enlisted
    0.82
     teamed
    0.79
    wrote
    0.79
     decided
    0.76
     undertook
    0.74
     embarked
    0.74
     redesigned
    0.74
     enlist
    0.74
    Act Density 0.584%

    No Known Activations