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

    Neuronpedia

    INDEX
    Explanations

    phrases strongly emphasizing the word "that"

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

    "that" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.86
     ModelExpression
    -0.77
    ContentAsync
    -0.70
    AndEndTag
    -0.67
    ValueStyle
    -0.65
    MessageState
    -0.64
    DockStyle
    -0.63
    ScopeManager
    -0.63
    ImageContext
    -0.62
    Sucesor
    -0.62
    POSITIVE LOGITS
     is
    0.70
     isn
    0.59
     was
    0.55
     iVar
    0.52
     makes
    0.51
     happens
    0.51
     doesn
    0.50
    ########.
    0.50
     has
    0.50
    mercial
    0.47
    Act Density 0.172%

    No Known Activations