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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating continuity or relatedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avr
    -0.16
    angu
    -0.15
    aton
    -0.15
    sdale
    -0.15
    ivant
    -0.15
    oles
    -0.14
    ENCHMARK
    -0.14
    íķľêµŃ
    -0.14
    oj
    -0.14
    olygon
    -0.13
    POSITIVE LOGITS
    erson
    0.28
    reas
    0.22
    amp
    0.20
    half
    0.19
     half
    0.18
    hra
    0.18
    AMP
    0.18
     amp
    0.18
    -half
    0.18
    /or
    0.17
    Act Density 0.353%

    No Known Activations