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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or intention

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating caution or carefulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.72
     respectively
    -0.60
     propelled
    -0.55
     inexpl
    -0.54
     counting
    -0.50
    ello
    -0.50
    glers
    -0.48
    EPA
    -0.47
    Released
    -0.46
     compounded
    -0.45
    POSITIVE LOGITS
     someday
    0.80
     responsibly
    0.69
     ASAP
    0.68
     yourselves
    0.67
     tomorrow
    0.65
     oneself
    0.63
     ourselves
    0.63
     yourself
    0.62
     anytime
    0.61
     sacrific
    0.60
    Act Density 1.671%

    No Known Activations