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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences or patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inflation
    -0.16
    ivid
    -0.15
    554
    -0.14
    olon
    -0.14
    orz
    -0.14
    usk
    -0.14
    質
    -0.14
     Trev
    -0.14
    führ
    -0.14
    dal
    -0.14
    POSITIVE LOGITS
    ucene
    0.17
    plusplus
    0.15
    AYOUT
    0.15
    .useState
    0.15
    Backing
    0.14
    lıģının
    0.14
    REFIX
    0.14
    kke
    0.14
    çķª
    0.14
     tune
    0.14
    Act Density 0.064%

    No Known Activations