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

    Neuronpedia

    INDEX
    Explanations

    references to oaths, vows, and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .metamodel
    -0.17
    hread
    -0.16
    opis
    -0.16
    ordion
    -0.16
    889
    -0.15
    ÐIJÑĢÑħÑĸв
    -0.15
    Insensitive
    -0.14
    mÃŃt
    -0.14
    گرÛĮ
    -0.14
    AutoSize
    -0.14
    POSITIVE LOGITS
     oath
    0.47
     swearing
    0.35
     sworn
    0.34
     swear
    0.33
     o
    0.32
     vows
    0.31
     pledge
    0.31
     vow
    0.31
    èª
    0.29
     pledges
    0.27
    Act Density 0.061%

    No Known Activations