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

    Neuronpedia

    INDEX
    Explanations

    discussions around political structures and representation of marginalized communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungal
    -0.17
    èĤ²
    -0.17
    ADED
    -0.16
     desn
    -0.16
    olid
    -0.16
    ativo
    -0.16
    373
    -0.15
    atten
    -0.15
    itters
    -0.14
    173
    -0.14
    POSITIVE LOGITS
     minorities
    0.39
     minority
    0.39
    minor
    0.35
    Minor
    0.35
     Minor
    0.35
     minor
    0.32
     Minority
    0.30
     marg
    0.28
     vulnerable
    0.26
     marginalized
    0.26
    Act Density 0.145%

    No Known Activations