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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases indicating observation or perception

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

    as you can see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preſent
    -0.46
     pleaſure
    -0.46
     fubject
    -0.44
    setFirstName
    -0.43
    tagHelperRunner
    -0.43
    istos
    -0.42
     Winaray
    -0.42
     uſe
    -0.40
     ſol
    -0.40
    word
    -0.40
    POSITIVE LOGITS
     clearly
    0.57
    ButterKnife
    0.53
    clearly
    0.52
    Clearly
    0.52
     claramente
    0.51
     clear
    0.50
     Clearly
    0.50
    IBOutlet
    0.48
    UnusedPrivate
    0.47
     snippetHide
    0.46
    Act Density 0.045%

    No Known Activations