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

    Neuronpedia

    INDEX
    Explanations

    different variations of the word "head" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oday
    -0.17
    agh
    -0.15
    pedia
    -0.15
    mland
    -0.14
    sonian
    -0.14
    ô
    -0.14
    gable
    -0.14
    iro
    -0.14
     Magnus
    -0.14
     Marr
    -0.14
    POSITIVE LOGITS
    lined
    0.23
    lining
    0.22
    quarter
    0.19
    liner
    0.18
    ecimal
    0.18
    itar
    0.18
    scar
    0.16
    quartered
    0.15
    gear
    0.15
     headed
    0.15
    Act Density 0.021%

    No Known Activations