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

    Neuronpedia

    INDEX
    Explanations

    instances of grid-related terms in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    しか
    -0.58
    andExpect
    -0.52
    matchCondition
    -0.52
    toEqual
    -0.51
     uit
    -0.51
    nmgp
    -0.51
     Clearly
    -0.49
     good
    -0.49
    rost
    -0.48
    Hochspringen
    -0.48
    POSITIVE LOGITS
    media
    1.16
     media
    1.15
     Media
    0.96
     MEDIA
    0.95
     Prints
    0.94
     prints
    0.92
    MEDIA
    0.90
    Grid
    0.90
    Media
    0.90
    grid
    0.88
    Act Density 0.119%

    No Known Activations