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

    Neuronpedia

    INDEX
    Explanations

    sentences that include comparative evaluations of features or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    withIdentifier
    -0.72
    ########.
    -0.65
    elemField
    -0.64
    OGND
    -0.62
    kháu
    -0.61
     consig
    -0.59
     verwijzen
    -0.58
    ardust
    -0.55
    gonic
    -0.54
    atguigu
    -0.54
    POSITIVE LOGITS
    GIVEREF
    0.57
     saites
    0.56
     resourceCulture
    0.51
    Datuak
    0.49
    انيف
    0.49
     صوتيه
    0.48
     CWE
    0.48
    이터
    0.46
    Спасылкі
    0.45
    IVERY
    0.44
    Act Density 0.032%

    No Known Activations