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

    Neuronpedia

    INDEX
    Explanations

    mentions that encourage community involvement or cooperation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sources
    -0.73
     Ahead
    -0.68
     Bang
    -0.68
    ãĥŁ
    -0.66
     Savings
    -0.66
     Cars
    -0.64
     Later
    -0.62
    Box
    -0.62
     VIDEOS
    -0.62
    IVERS
    -0.60
    POSITIVE LOGITS
     specialize
    0.91
     disagrees
    0.76
    ereo
    0.74
     satisfies
    0.74
     bothers
    0.73
     qualifies
    0.72
     compares
    0.72
     distinguishes
    0.72
    ertodd
    0.72
     genuinely
    0.70
    Act Density 0.168%

    No Known Activations