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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    words related to love and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.91
    cffffcc
    -0.71
     tremend
    -0.70
     variance
    -0.68
     looph
    -0.68
    omaly
    -0.67
    tnc
    -0.65
     biom
    -0.65
     lapt
    -0.65
     barrier
    -0.64
    POSITIVE LOGITS
    rences
    0.88
    ancial
    0.85
    doms
    0.79
    nder
    0.77
    eworks
    0.72
    ason
    0.71
    ciples
    0.71
    enstein
    0.70
    heit
    0.69
    ocket
    0.69
    Act Density 0.078%

    No Known Activations