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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "additional" and variations related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tram
    -0.16
    vester
    -0.14
    oton
    -0.14
    اش
    -0.14
    INVAL
    -0.13
    avourites
    -0.13
    .SIG
    -0.13
    aque
    -0.13
    LY
    -0.13
    paste
    -0.13
    POSITIVE LOGITS
    ordin
    0.18
    halb
    0.17
    ño
    0.16
    /new
    0.15
    dued
    0.15
    ÏģÏī
    0.15
    /sub
    0.15
    CTION
    0.15
    ¤í
    0.15
    nist
    0.14
    Act Density 0.020%

    No Known Activations