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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the word "certain."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĨÙĩ
    -0.19
    ust
    -0.16
    ses
    -0.15
    åIJĦç§į
    -0.15
    iske
    -0.15
    side
    -0.15
    sv
    -0.14
     stuff
    -0.14
    session
    -0.14
     sheer
    -0.13
    POSITIVE LOGITS
     kinds
    0.28
    ç¨ĭ度
    0.24
    amount
    0.23
     types
    0.23
     amount
    0.23
    -sex
    0.20
     aspects
    0.19
    ;y
    0.19
    /all
    0.18
     обÑĢазом
    0.18
    Act Density 0.032%

    No Known Activations