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

    Neuronpedia

    INDEX
    Explanations

    references to electrical sockets

    oai_token-act-pair · gpt-3.5-turbo

    references to computer hardware components, particularly related to sockets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lys
    -0.68
    birth
    -0.65
    hig
    -0.65
    ORGE
    -0.65
     Ames
    -0.65
    ATHER
    -0.65
    enez
    -0.64
     Lerner
    -0.63
    gary
    -0.63
     Cao
    -0.61
    POSITIVE LOGITS
     socket
    1.03
     sockets
    0.99
    socket
    0.99
     Socket
    0.97
    rings
    0.88
     wrench
    0.84
    nown
    0.81
    acles
    0.80
    uitous
    0.79
    onite
    0.76
    Act Density 0.042%

    No Known Activations