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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with structured numerical or categorical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itto
    -0.16
    ellen
    -0.15
    ulum
    -0.14
    antt
    -0.14
    )(__
    -0.14
    åı¦å¤ĸ
    -0.13
    Äĥm
    -0.13
    ières
    -0.13
    plib
    -0.13
    igest
    -0.13
    POSITIVE LOGITS
    tee
    0.17
    son
    0.14
    tees
    0.14
     Hoover
    0.14
     Awakening
    0.14
    po
    0.14
     gear
    0.13
    ãĢģä¸ī
    0.13
    $MESS
    0.13
     Lydia
    0.13
    Act Density 0.138%

    No Known Activations