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

    Neuronpedia

    INDEX
    Explanations

    timestamps and time zones in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time zones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pir
    -0.76
    itably
    -0.74
    proof
    -0.70
    kers
    -0.70
    bestos
    -0.69
    proxy
    -0.69
    gettable
    -0.68
    acters
    -0.67
     affirmative
    -0.65
    hist
    -0.65
    POSITIVE LOGITS
     PDT
    0.91
    DAQ
    0.85
    EMBER
    0.84
     PST
    0.79
     Lumpur
    0.78
     CET
    0.74
    GMT
    0.72
     EDT
    0.72
    ember
    0.71
    ICAN
    0.70
    Act Density 0.005%

    No Known Activations