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

    Neuronpedia

    INDEX
    Explanations

    instances of being taken or placed somewhere

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     capitals
    -0.67
     tradition
    -0.66
     Confeder
    -0.65
     fortunes
    -0.64
     Alps
    -0.63
     occurrence
    -0.62
     insurg
    -0.61
     convergence
    -0.61
     ingenuity
    -0.61
     stripe
    -0.61
    POSITIVE LOGITS
     aback
    0.99
     handcuffed
    0.85
     Reincarnated
    0.81
    uled
    0.80
     medically
    0.80
     deported
    0.78
    quished
    0.77
     by
    0.75
     prisoner
    0.74
     hostage
    0.73
    Act Density 0.348%

    No Known Activations