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

    Neuronpedia

    INDEX
    Explanations

    repetitive conjunctions and discourse markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aspers
    -0.17
    gia
    -0.16
    gamber
    -0.15
    ETHOD
    -0.15
    ye
    -0.14
    terdam
    -0.14
    ayette
    -0.14
    iano
    -0.14
    orgen
    -0.13
    eyed
    -0.13
    POSITIVE LOGITS
    rei
    0.18
    reas
    0.18
    rea
    0.17
    ree
    0.15
    uids
    0.15
    rie
    0.15
    esine
    0.14
    zs
    0.14
    çī©
    0.14
     ìĭ¶
    0.14
    Act Density 0.148%

    No Known Activations