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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a generalized concept or unspecified thing

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "anything" or unspecified subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fer
    -0.72
    irth
    -0.70
     anonymity
    -0.67
    ardi
    -0.67
    arb
    -0.66
    nec
    -0.65
    asio
    -0.64
    ritz
    -0.63
     Encyclopedia
    -0.63
    ulators
    -0.62
    POSITIVE LOGITS
     else
    1.69
    Else
    1.35
     resembling
    1.26
     Else
    1.10
    else
    0.97
    THING
    0.94
     remotely
    0.94
     imaginable
    0.93
     whatsoever
    0.88
     happens
    0.85
    Act Density 0.046%

    No Known Activations