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

    Neuronpedia

    INDEX
    Explanations

    the presence and structure of mathematical definitions and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩe
    -0.16
    pler
    -0.16
    loor
    -0.15
    herits
    -0.14
    riends
    -0.14
    ihan
    -0.14
    umd
    -0.13
    ilter
    -0.13
    retty
    -0.13
    ngrx
    -0.13
    POSITIVE LOGITS
    ucci
    0.18
     agent
    0.16
    agent
    0.16
     Chop
    0.16
     Agent
    0.15
    .yy
    0.14
     magn
    0.14
     chops
    0.14
    adera
    0.14
     Governor
    0.14
    Act Density 0.021%

    No Known Activations