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

    Neuronpedia

    INDEX
    Explanations

    references to "base" and related terminologies in a technical context

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

    "Base" followed by specific suffixes

    np_acts-logits-general · gemini-2.0-flash

    base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diwedd
    -0.47
     ligiloj
    -0.47
    Ikus
    -0.42
    ณ์
    -0.42
    kijken
    -0.41
    tamment
    -0.40
     kijken
    -0.39
     pelúcia
    -0.39
     actionPerformed
    -0.39
     Though
    -0.38
    POSITIVE LOGITS
     Base
    1.23
     BASE
    1.19
     getBase
    1.13
     base
    1.12
    Base
    1.07
    base
    1.03
    BASE
    0.98
    bases
    0.82
    getBase
    0.81
    IBase
    0.80
    Act Density 0.060%

    No Known Activations