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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation

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

    numbered list starting point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Speck
    -0.53
    tiness
    -0.52
     AGENCY
    -0.52
     قهر
    -0.51
    typeorm
    -0.50
    ceria
    -0.50
     Cordero
    -0.48
    carbonyl
    -0.48
     ANGEL
    -0.47
    orkin
    -0.47
    POSITIVE LOGITS
     houſe
    0.45
     ſte
    0.44
     surla
    0.43
     ſtre
    0.43
    melidir
    0.43
     Lingkungan
    0.42
     ſta
    0.42
     himſelf
    0.41
     ſhe
    0.40
     avoient
    0.39
    Act Density 0.009%

    No Known Activations