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

    Neuronpedia

    INDEX
    Explanations

    the word "only" along with variations of numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aleza
    -0.18
    boro
    -0.17
    ICODE
    -0.15
    oose
    -0.15
    ibal
    -0.15
    稿
    -0.14
     ArgumentNullException
    -0.14
    à¸ĩศ
    -0.14
    γκα
    -0.14
    oya
    -0.14
    POSITIVE LOGITS
    ere
    0.14
    éri
    0.14
     qual
    0.14
    esity
    0.14
     Ñģоп
    0.14
     spheres
    0.13
    umi
    0.13
    ment
    0.13
    urma
    0.13
     registered
    0.13
    Act Density 0.043%

    No Known Activations