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

    Neuronpedia

    INDEX
    Explanations

    phrases related to articles and subjective evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.62
    ыгана
    -0.57
     feroit
    -0.55
    ंदीखरीदारी
    -0.55
     Riproduzione
    -0.54
     CURIAM
    -0.52
     waited
    -0.51
     foule
    -0.50
    empereur
    -0.49
     Pièces
    -0.49
    POSITIVE LOGITS
     shot
    1.30
     go
    0.99
     whirl
    0.98
     crack
    0.97
     try
    0.97
    shot
    0.90
     stab
    0.88
     Shot
    0.88
     SHOT
    0.82
    Shot
    0.81
    Act Density 0.260%

    No Known Activations