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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like" indicating comparison or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzey
    -0.16
    argas
    -0.15
    iry
    -0.14
    arger
    -0.14
    urus
    -0.14
     hung
    -0.14
    asje
    -0.13
    alue
    -0.13
    ç¾
    -0.13
    ÃŃf
    -0.13
    POSITIVE LOGITS
    stoff
    0.15
    esson
    0.15
    abcdefghijkl
    0.15
    _utilities
    0.15
    thane
    0.15
    ests
    0.15
    frm
    0.14
    ĸī
    0.14
    andes
    0.14
    forme
    0.14
    Act Density 0.014%

    No Known Activations