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

    Neuronpedia

    INDEX
    Explanations

    examples of expressions featuring the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivec
    -0.17
    -ci
    -0.16
    ãĥ³ãĥIJ
    -0.16
    ihat
    -0.14
    ÑĢаÑĩ
    -0.14
    axon
    -0.14
    occo
    -0.14
    bach
    -0.14
    lichen
    -0.14
    å¯Ĩ
    -0.14
    POSITIVE LOGITS
    agen
    0.17
    agas
    0.15
    upert
    0.13
    steen
    0.13
     Murdoch
    0.13
    uest
    0.13
     gab
    0.13
    lete
    0.13
     Westbrook
    0.13
    laus
    0.13
    Act Density 0.039%

    No Known Activations