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

    Neuronpedia

    INDEX
    Explanations

    references to depth in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    in-depth investigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.75
     pouvoit
    -0.74
    astify
    -0.72
    Искәрмәләр
    -0.69
    windowFixed
    -0.68
    thâu
    -0.67
    LookAnd
    -0.67
     queſta
    -0.66
     feroit
    -0.63
    ✨:
    -0.62
    POSITIVE LOGITS
    depth
    1.59
     depth
    1.48
    Depth
    1.37
     Depth
    1.36
    DEPTH
    1.18
     DEPTH
    1.09
     profundidad
    0.99
    深度
    0.93
     deep
    0.91
     depths
    0.90
    Act Density 0.005%

    No Known Activations