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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or desire, particularly concerning desired places or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.81
     offsets
    -0.72
     Pattern
    -0.64
     predictive
    -0.63
     Causes
    -0.63
     costing
    -0.63
     batches
    -0.63
     warrants
    -0.62
     Truman
    -0.62
    requires
    -0.62
    POSITIVE LOGITS
     explore
    1.05
     discuss
    1.01
     communicate
    1.01
     reside
    0.97
     learn
    0.96
     dwell
    0.91
     interact
    0.90
     organize
    0.90
     indulge
    0.88
     educate
    0.88
    Act Density 0.067%

    No Known Activations