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

    Neuronpedia

    INDEX
    Explanations

    phrases that concern conditions or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NewReader
    -0.73
    ✨:
    -0.71
    fromnode
    -0.70
    riculum
    -0.70
     Monfieur
    -0.69
     Diſ
    -0.65
     acrylique
    -0.65
     pleaſure
    -0.65
     bezeichneter
    -0.64
     betweenstory
    -0.64
    POSITIVE LOGITS
     terms
    1.38
     Terms
    1.03
     TERMS
    1.01
    terms
    0.99
    Terms
    0.91
     termes
    0.90
     termos
    0.89
    TERMS
    0.80
     términos
    0.72
     regards
    0.65
    Act Density 0.062%

    No Known Activations