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

    Neuronpedia

    INDEX
    Explanations

    words related to comprehension and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelper
    -0.74
    arbox
    -0.64
     Astor
    -0.63
    番
    -0.61
    zości
    -0.61
     Grossman
    -0.61
    jupiter
    -0.59
    الثة
    -0.59
     colpo
    -0.58
    glBindTexture
    -0.58
    POSITIVE LOGITS
    understand
    1.56
     Understand
    1.54
     understand
    1.51
    Understand
    1.50
     understands
    1.48
     understanding
    1.44
    understood
    1.36
     understood
    1.35
    understanding
    1.34
     understandings
    1.32
    Act Density 0.069%

    No Known Activations