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

    Neuronpedia

    INDEX
    Explanations

    references to linear relationships and equations in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iw
    -0.18
     Bol
    -0.15
     Thick
    -0.15
    oles
    -0.15
    agal
    -0.14
     Skinner
    -0.14
    awi
    -0.14
    award
    -0.14
    ib
    -0.14
     margin
    -0.14
    POSITIVE LOGITS
    atica
    0.18
    nez
    0.16
    ichier
    0.16
    عÙĬ
    0.15
     èĩªåĬ¨çĶŁæĪIJ
    0.15
    WindowTitle
    0.14
    áty
    0.14
    ized
    0.14
    ivy
    0.14
     Cald
    0.14
    Act Density 0.030%

    No Known Activations