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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their contexts, likely related to measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Revival
    -0.78
     Chevy
    -0.75
     Denny
    -0.73
     Conrad
    -0.72
     Grady
    -0.72
     BUSH
    -0.70
    Grady
    -0.68
    Denny
    -0.67
    Conrad
    -0.66
     Bajaj
    -0.66
    POSITIVE LOGITS
     Christensen
    0.85
     Ziegler
    0.81
     Singh
    0.80
     Pereira
    0.79
     Saad
    0.79
     Alexandra
    0.77
    Pere
    0.75
     Norton
    0.75
     McKenzie
    0.74
     Raquel
    0.73
    Act Density 1.760%

    No Known Activations