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

    Neuronpedia

    INDEX
    Explanations

    dates or phrases related to scheduling meetings

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subtract
    -0.78
     bleed
    -0.71
     restitution
    -0.69
     knots
    -0.66
    ifles
    -0.65
     mortgages
    -0.65
    DNA
    -0.64
     genes
    -0.63
     lin
    -0.63
     uninsured
    -0.63
    POSITIVE LOGITS
     convened
    1.22
     chaired
    1.09
     hosted
    1.01
    conference
    0.97
     keynote
    0.86
     presided
    0.85
    posium
    0.84
    nesday
    0.84
     held
    0.82
     Held
    0.82
    Act Density 0.255%

    No Known Activations