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

    Neuronpedia

    INDEX
    Explanations

    terms related to data collection and analysis technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _campaign
    -0.15
    linger
    -0.14
    agar
    -0.14
     kariy
    -0.14
    enga
    -0.14
     Shift
    -0.14
    bian
    -0.14
     lever
    -0.13
    νι
    -0.13
    ledge
    -0.13
    POSITIVE LOGITS
     treatment
    0.15
    utzer
    0.14
     konkrét
    0.13
    ettel
    0.13
    Treatment
    0.13
    ADIUS
    0.13
    igen
    0.13
     eg
    0.13
     Treatment
    0.13
    æĵļ
    0.13
    Act Density 0.120%

    No Known Activations