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

    Neuronpedia

    INDEX
    Explanations

    complex sentence structures and punctuation

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

    preceding causal conjunctions

    np_acts-logits-general · gemini-2.0-flash

    resulting or leading to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.69
     Савезне
    -0.64
    JsonHelper
    -0.63
    ціаль
    -0.61
    yorlar
    -0.61
     Etc
    -0.60
    (_,
    -0.59
    InvalidProtocol
    -0.58
     вроде
    -0.58
     Италијани
    -0.57
    POSITIVE LOGITS
     resulting
    0.73
     ensuring
    0.69
     enabling
    0.67
     providing
    0.67
     giving
    0.65
     allowing
    0.63
     making
    0.60
    resulting
    0.60
     garant
    0.59
     vilket
    0.58
    Act Density 0.510%

    No Known Activations