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

    Neuronpedia

    INDEX
    Explanations

    email addresses with specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    email addresses and contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scheme
    -0.86
     Passive
    -0.86
     Warning
    -0.84
     Pressure
    -0.82
     Thunderbolt
    -0.82
     Decay
    -0.81
     Kut
    -0.81
     Enabled
    -0.81
     Ninth
    -0.81
     Scale
    -0.80
    POSITIVE LOGITS
    @
    1.05
    iverpool
    1.04
    mc
    0.94
    christ
    0.94
    olson
    0.92
     americ
    0.91
    anders
    0.90
    yond
    0.90
    podcast
    0.90
    izabeth
    0.90
    Act Density 0.435%

    No Known Activations