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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote equality or comparisons involving numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ramirez
    -0.14
    071
    -0.14
    ProgressHUD
    -0.14
    irq
    -0.14
    uš
    -0.14
    roti
    -0.14
    ypsum
    -0.13
    rière
    -0.13
    uni
    -0.13
    rored
    -0.13
    POSITIVE LOGITS
    ilage
    0.16
    ç»ĵ
    0.16
    stru
    0.15
    ittest
    0.15
    ouses
    0.14
    าว
    0.14
    ffic
    0.14
    害
    0.14
    ocation
    0.14
    aylor
    0.14
    Act Density 0.016%

    No Known Activations