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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hers
    -0.15
    icide
    -0.14
    unce
    -0.14
    alte
    -0.14
    982
    -0.13
    udget
    -0.13
    acity
    -0.13
    985
    -0.13
    _macros
    -0.13
    C
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥĬ
    0.17
    yaw
    0.17
    ênh
    0.16
    LEM
    0.15
     Bram
    0.15
     embr
    0.15
    auge
    0.14
    mÄĽ
    0.14
    oids
    0.14
    lund
    0.13
    Act Density 0.092%

    No Known Activations