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

    Neuronpedia

    INDEX
    Explanations

    positive interactions between law enforcement officers and members of the community

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     impra
    -0.84
     overla
    -0.83
     mef
    -0.78
     unve
    -0.78
     impractica
    -0.76
     compen
    -0.76
     wherea
    -0.75
     arbitrar
    -0.74
     dsg
    -0.73
     Simult
    -0.73
    POSITIVE LOGITS
     youth
    0.57
    Brainz
    0.53
     drugs
    0.53
     drug
    0.51
     teenage
    0.49
    spender
    0.49
     rehabilitation
    0.49
    ineno
    0.49
     initState
    0.49
     onStop
    0.49
    Act Density 0.532%

    No Known Activations