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

    Neuronpedia

    INDEX
    Explanations

    terms related to averages and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grad
    -0.16
    -0.15
    ãĥ¼ãĥĬ
    -0.14
     below
    -0.14
    estone
    -0.14
     Nets
    -0.14
    214
    -0.14
    缤
    -0.14
    estation
    -0.13
     Barton
    -0.13
    POSITIVE LOGITS
    tok
    0.17
    ieres
    0.16
    ardo
    0.16
    andas
    0.15
    ires
    0.15
     takson
    0.14
     itemprop
    0.14
    imary
    0.14
    owitz
    0.14
     경기ëıĦ
    0.14
    Act Density 0.020%

    No Known Activations