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

    Neuronpedia

    INDEX
    Explanations

    phrases related to depth and intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    761
    -0.16
    .scalablytyped
    -0.16
    pic
    -0.15
    lauf
    -0.15
    okol
    -0.15
    essor
    -0.14
    oline
    -0.14
    ãĥĨãĥ«
    -0.14
    BOARD
    -0.14
    ÙĦÙģ
    -0.14
    POSITIVE LOGITS
     deep
    0.30
    deep
    0.28
     deepest
    0.28
    ening
    0.25
    Deep
    0.24
    æ·±
    0.24
     depths
    0.23
     deeper
    0.23
     Deep
    0.23
    ened
    0.21
    Act Density 0.057%

    No Known Activations