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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements and statistical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.88
    giaan
    -0.77
     Decken
    -0.73
    ̸
    -0.69
    pédie
    -0.68
    Elise
    -0.67
    ilever
    -0.65
    DISTR
    -0.64
    helves
    -0.62
    NDE
    -0.62
    POSITIVE LOGITS
     shots
    1.63
     shot
    1.58
     shoots
    1.52
    Shots
    1.51
     Shots
    1.51
     SHOT
    1.46
     Shot
    1.43
    shot
    1.39
    shots
    1.38
     shoot
    1.37
    Act Density 0.073%

    No Known Activations