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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consumer choice and advocacy

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     cannibal
    -0.68
    hov
    -0.66
    loss
    -0.64
     heresy
    -0.64
     incompetence
    -0.64
    death
    -0.63
     arson
    -0.63
     Decay
    -0.62
     sarc
    -0.62
     obsc
    -0.60
    POSITIVE LOGITS
     understand
    1.02
     access
    0.93
     informed
    0.92
     understands
    0.92
     realise
    0.89
     participate
    0.89
     accessible
    0.88
     aware
    0.88
     opportunities
    0.84
     opportunity
    0.83
    Act Density 0.416%

    No Known Activations