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

    Neuronpedia

    INDEX
    Explanations

    names of conferences and meetings

    oai_token-act-pair · gpt-3.5-turbo

    references to meetings and conferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     revenge
    -0.80
     deserts
    -0.69
    Ö
    -0.69
    utterstock
    -0.69
     spiral
    -0.68
     mars
    -0.68
    livion
    -0.67
     ruining
    -0.66
     havoc
    -0.66
     survives
    -0.66
    POSITIVE LOGITS
     attendees
    1.27
     keynote
    1.24
     Attend
    1.12
     chaired
    1.10
     convened
    1.07
     speakers
    1.04
     delegates
    1.02
     representatives
    1.02
     Representatives
    1.02
     discussing
    1.02
    Act Density 0.426%

    No Known Activations