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

    Neuronpedia

    INDEX
    Explanations

    the word "do" regardless of context

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "do"

    np_token-act-pair-logits · gpt-4o-mini

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.74
    expandindo
    -0.72
     مشين
    -0.72
     GetEnumerator
    -0.58
    EndProject
    -0.57
     Chriftian
    -0.57
    IsContent
    -0.57
    stdc
    -0.56
    AndEndTag
    -0.56
    GraphicsUnit
    -0.56
    POSITIVE LOGITS
    StartTag
    0.49
     CreateTagHelper
    0.48
    enumi
    0.45
    __:
    0.44
    })}$
    0.42
    LookAnd
    0.42
    setAccessible
    0.41
    =',
    0.41
     not
    0.41
    AxisAlignment
    0.41
    Act Density 0.272%

    No Known Activations