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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "there" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MAKES
    -0.43
     itself
    -0.42
     Makes
    -0.41
    satisfies
    -0.40
    Makes
    -0.40
    makes
    -0.39
     uses
    -0.39
     makes
    -0.39
    Bretagne
    -0.39
     Brabant
    -0.38
    POSITIVE LOGITS
    ValueStyle
    0.84
    AddTagHelper
    0.65
    脚注の使い方
    0.64
     ब्रेकडाउन
    0.63
     Taktlose
    0.61
    IntoConstraints
    0.60
    InitVars
    0.57
    awtextra
    0.57
     gyhoeddwyd
    0.56
    ьаж
    0.55
    Act Density 0.155%

    No Known Activations