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

    Neuronpedia

    INDEX
    Explanations

    technical issues or bugs mentioned in software release notes

    oai_token-act-pair · gpt-3.5-turbo

    references to software bugs and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iolet
    -0.82
    pin
    -0.81
    ategic
    -0.77
    oliberal
    -0.77
    imb
    -0.75
     Pants
    -0.73
    rients
    -0.72
    uries
    -0.71
    asha
    -0.71
    shi
    -0.71
    POSITIVE LOGITS
     workaround
    1.01
     plag
    0.91
     CVE
    0.85
     bug
    0.84
     tracker
    0.81
     disabling
    0.78
     havoc
    0.77
    bug
    0.77
     testers
    0.76
     annoyance
    0.74
    Act Density 0.078%

    No Known Activations