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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to biases and statistical analysis in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    782
    -0.15
    reira
    -0.14
    quina
    -0.14
    irma
    -0.14
     Sloven
    -0.13
     RNA
    -0.13
     Qi
    -0.13
    TEGER
    -0.13
    celand
    -0.13
    Borders
    -0.13
    POSITIVE LOGITS
     Daisy
    0.40
     Fitzgerald
    0.39
     Jay
    0.35
    Jay
    0.31
    atsby
    0.28
     Jordan
    0.27
     Buchanan
    0.27
     Nick
    0.27
     G
    0.27
     Zelda
    0.26
    Act Density 0.007%

    No Known Activations