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

    Neuronpedia

    INDEX
    Explanations

    technical information such as names, dates, and details

    oai_token-act-pair · gpt-3.5-turbo

    information related to disclaimers, site affiliations, and online content ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.69
     attRot
    -0.68
    $.
    -0.63
    theless
    -0.60
    Ire
    -0.59
     mosqu
    -0.57
    etheless
    -0.55
    ogether
    -0.54
    tnc
    -0.51
     suscept
    -0.50
    POSITIVE LOGITS
     [-
    0.71
     [/
    0.65
     [+
    0.65
    )</
    0.64
     ..."
    0.62
     (%
    0.58
     ·
    0.56
    ?'
    0.55
     </
    0.55
     `
    0.55
    Act Density 2.337%

    No Known Activations