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

    Neuronpedia

    INDEX
    Explanations

    references to local engagement and community involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onne
    -0.17
    ån
    -0.15
     escorte
    -0.15
    eltas
    -0.14
    ffen
    -0.14
    ield
    -0.14
    idon
    -0.14
    íĥķ
    -0.14
    .scenes
    -0.14
    ksen
    -0.14
    POSITIVE LOGITS
     interest
    0.37
     Express
    0.35
     expressed
    0.34
    express
    0.33
     Interest
    0.33
     applied
    0.32
     expressing
    0.32
     expresses
    0.31
     expressions
    0.31
     interested
    0.31
    Act Density 0.181%

    No Known Activations