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

    Neuronpedia

    INDEX
    Explanations

    specific keywords or phrases throughout various texts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the letter 's'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CVE
    -0.63
     scares
    -0.63
     elector
    -0.63
    eur
    -0.62
     subcontract
    -0.60
     Lauder
    -0.60
     extermination
    -0.58
     caffe
    -0.58
    ãĤ¹ãĥĪ
    -0.57
    mass
    -0.57
    POSITIVE LOGITS
    ashtra
    0.85
    forth
    0.78
    !--
    0.78
    ername
    0.78
    terday
    0.76
    wered
    0.72
    omew
    0.70
    aurus
    0.69
    abi
    0.68
    pecially
    0.68
    Act Density 0.049%

    No Known Activations