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

    Neuronpedia

    INDEX
    Explanations

    phrases related to certification or verification processes

    oai_token-act-pair · gpt-3.5-turbo

    references to Equifax and related terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.81
     calming
    -0.66
     seeing
    -0.64
     hanging
    -0.64
     fabricated
    -0.64
    ball
    -0.63
    stal
    -0.63
     fog
    -0.61
     dear
    -0.61
     living
    -0.60
    POSITIVE LOGITS
    ifax
    1.28
    ivalent
    1.21
    ipment
    1.15
    ivil
    1.10
    ilibrium
    1.07
    ilib
    1.01
    isons
    0.98
    als
    0.98
    rera
    0.96
    idable
    0.94
    Act Density 0.007%

    No Known Activations