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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating additional information or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comigo
    -0.83
     femininas
    -0.76
    addContainerGap
    -0.75
     femininos
    -0.75
     felizes
    -0.74
    تفصیلات
    -0.74
     sukker
    -0.74
     brancas
    -0.72
     pinulongan
    -0.71
    الإنجليزية
    -0.71
    POSITIVE LOGITS
     ens
    0.61
     emp
    0.60
     also
    0.57
     simply
    0.56
     Simply
    0.55
     focus
    0.54
     focused
    0.53
    Simply
    0.52
    ValueStyle
    0.51
    manjaro
    0.51
    Act Density 0.139%

    No Known Activations