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

    Neuronpedia

    INDEX
    Explanations

    references to meetings or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Malay
    -0.66
    ьаж
    -0.66
    fortune
    -0.65
    polate
    -0.63
     defStyle
    -0.61
     Lowe
    -0.60
     fortune
    -0.60
    øya
    -0.60
    iyle
    -0.60
     Adamson
    -0.60
    POSITIVE LOGITS
     meetings
    2.03
     Meetings
    1.98
     Meeting
    1.93
     meeting
    1.91
    Meetings
    1.80
    Meeting
    1.80
    meeting
    1.78
    meetings
    1.70
     MEETING
    1.67
    ETING
    1.23
    Act Density 0.085%

    No Known Activations