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

    Neuronpedia

    INDEX
    Explanations

    terms related to foundational concepts and potential in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oben
    -0.53
    нав
    -0.53
    맞
    -0.51
     sna
    -0.50
    Rcpp
    -0.50
    stin
    -0.49
    ariste
    -0.49
    std
    -0.49
    пре
    -0.48
     Sna
    -0.48
    POSITIVE LOGITS
     незавершена
    1.00
     itſelf
    0.92
     potential
    0.91
     themſelves
    0.91
    potential
    0.86
     foundation
    0.83
     ſtate
    0.82
     ſeveral
    0.81
    Potential
    0.80
    tanleria
    0.80
    Act Density 0.110%

    No Known Activations