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

    Neuronpedia

    INDEX
    Explanations

    references to reading and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    939
    -0.15
    ia
    -0.15
    igh
    -0.15
    zel
    -0.15
    ce
    -0.14
    g
    -0.14
     Bender
    -0.14
    yu
    -0.14
    c
    -0.14
    ren
    -0.14
    POSITIVE LOGITS
    ÐIJÑĢÑħÑĸв
    0.17
    /***/
    0.17
    .LookAndFeel
    0.16
    riot
    0.16
    âĦĸâĦĸ
    0.16
    ìĽĶë¶ĢíĦ°
    0.16
    TestCategory
    0.15
     mrt
    0.14
     prostitutas
    0.14
    toi
    0.14
    Act Density 0.106%

    No Known Activations