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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong relationship or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closely related/similar/associated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indígen
    -0.59
     palvel
    -0.51
    Portail
    -0.50
     Geiſt
    -0.50
    })*/
    -0.49
     unſer
    -0.48
     Paglinawan
    -0.48
     maș
    -0.47
    Fonto
    -0.47
     increí
    -0.47
    POSITIVE LOGITS
     closely
    1.93
     tightly
    1.02
     étro
    0.81
    密切
    0.75
     keenly
    0.70
     intently
    0.69
     estrecha
    0.69
    tight
    0.69
    紧
    0.68
     carefully
    0.65
    Act Density 0.005%

    No Known Activations