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

    Neuronpedia

    INDEX
    Explanations

    phrases that repeat the same word, particularly with an emphasis or comparison

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    UME
    -0.76
    Reviewer
    -0.74
    AMI
    -0.72
    ERAL
    -0.70
    ogi
    -0.70
    andr
    -0.70
    ettle
    -0.67
    orge
    -0.67
    CHAT
    -0.65
    oes
    -0.65
    POSITIVE LOGITS
     consecut
    0.89
    theless
    0.89
     apiece
    0.72
    fold
    0.72
     dipping
    0.69
     dozen
    0.69
     thirds
    0.65
     Eleven
    0.64
    entimes
    0.63
     halves
    0.62
    Act Density 0.018%

    No Known Activations