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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating procedural or instructional context

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

    "as" followed by a verb or adverb

    np_acts-logits-general · gemini-2.0-flash

    introduces comparison or method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.90
    IVEREF
    -0.77
    httphttps
    -0.71
    ArrowToggle
    -0.65
    +#+#
    -0.63
     informée
    -0.60
    AddHtmlAttribute
    -0.59
    CodedInputStream
    -0.59
     Infórmanos
    -0.58
     Paglinawan
    -0.58
    POSITIVE LOGITS
    done
    0.62
     done
    0.62
    ///</
    0.48
     usual
    0.43
     we
    0.42
     suggested
    0.40
     sucedió
    0.39
     she
    0.39
     did
    0.38
    Done
    0.37
    Act Density 0.327%

    No Known Activations